Pre-computed context
check's tool probes ran at load time. Read these rows instead of re-issuing them; each shows the
tool's path when present, or absent when missing:
jq: !command -v jq 2>/dev/null || echo absent
curl: !command -v curl 2>/dev/null || echo absent
awk: !command -v awk 2>/dev/null || echo absent
sort: !command -v sort 2>/dev/null || echo absent
A row reading [shell command execution disabled by policy] carries no result: run that tool's
command -v probe via Bash instead.
Purpose
Setup per the uniform setup contract (docs/plugin-philosophy.md "Setup is explicit and repeatable" in
the marketplace repository): check inspects and reports, apply resolves. This plugin declares no
userConfig, and has two setup concerns:
- the external command-line tools its bundled scripts require, where
apply is guidance-and-verify
with no write path: it points at platform install instructions and never installs a system package;
- the tracked consumer-project configuration
audit and audit-pass read, the suppressions
mapping of <home>/harness-config.yaml, the one file apply may write. <home> is the
convention home the repository binds in the pointer region of its AGENTS.md or CLAUDE.md
(bash ${CLAUDE_PLUGIN_ROOT}/lib/resolve-convention-home.sh prints it), else docs/conventions.
Action routing: no argument or check runs the check; apply runs the check first, then remediation;
wsl-profile runs only its own section. All are non-interactive, so never prompt when the action is given.
check (read-only)
The bundled scripts are the single source of truth for what this plugin requires.
Read it first. Probe what it actually does, don't recite this file. Then read the
pre-computed tool rows, run the remaining probes via Bash, and report a PASS/FAIL/INFO table with one remediation line per FAIL. Do not modify anything.
The runtime scripts and their tools:
${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/check-plugin-drift.sh: jq and curl
${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/check-structure.sh, check-hook-coverage.sh and fix-plugin-drift.sh: jq
${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/audit-engine.sh: jq plus awk and sort; check-effort-pins.sh: jq plus awk
${CLAUDE_PLUGIN_ROOT}/skills/audit-automation-gaps/scripts/inventory.sh: jq plus awk
${CLAUDE_PLUGIN_ROOT}/skills/audit-permission-grants/scripts/permission-rule-check.sh: jq plus awk and sort
${CLAUDE_PLUGIN_ROOT}/skills/audit-permission-state/scripts/*.sh: jq (required; permission-state.sh exits 2 without it), awk and sort; automode-block-lint.sh and automode-entry-diff.sh add python3 for an optional lane
${CLAUDE_PLUGIN_ROOT}/skills/draft-auto-mode-rules/scripts/draft-automode-block.sh: jq
${CLAUDE_PLUGIN_ROOT}/skills/audit-pass/scripts/run-state.sh: jq (falls back to python3, then to a scan that announces itself)
${CLAUDE_PLUGIN_ROOT}/lib/check-retirements.sh: awk (no jq)
${CLAUDE_PLUGIN_ROOT}/skills/audit-pass/scripts/state-digest.sh and finding-identity.sh: sort
${CLAUDE_PLUGIN_ROOT}/skills/audit-instructions/scripts/instruction-scan.sh: grep, tr and awk (no jq)
${CLAUDE_PLUGIN_ROOT}/skills/audit-instructions/scripts/conflict-scan.sh: awk and sort (no jq)
Most scripts that need jq probe for it, but only conflict-scan.sh and instruction-scan.sh probe
for awk and sort; the rest call those with no guard, so read each script's actual calls rather than trusting a single script's prerequisite block to
speak for the plugin.
jq, from the pre-computed jq row. FAIL if absent: the JSON-parsing scripts need it (inventory.sh degrades
to an empty inventory; the others exit 2 with an install remediation). Missing jq blocks every
skill whose scripts parse JSON (audit, audit-automation-gaps, audit-permission-grants,
audit-permission-state, draft-auto-mode-rules, and audit-pass's run-state helper); audit-instructions scans markdown and is unaffected.
curl, from the pre-computed curl row. FAIL if absent, but scoped: only the plugin-drift check
(check-plugin-drift.sh) uses it and exit 2s without it. The rest of audit and every other
skill still run; say so in the remediation line.
awk and sort, from the pre-computed awk and sort rows. FAIL if either is absent, and not
scoped to one skill: conflict-scan.sh and instruction-scan.sh probe and exit 2 naming the
missing one, while the other scripts in the list above that use them have no prerequisite check
at all, so their skills fail mid-run on a bare command not found rather than on a named
prerequisite. Say in the
remediation line that this FAIL reaches six skills (audit, audit-automation-gaps,
audit-pass, audit-permission-grants, audit-permission-state and audit-instructions), not
just audit-instructions. Report awk and sort by name rather than as one row, since a
minimal shell can carry one and not the other.
- Bash shell, INFO: the scripts are bash (arrays,
[[ ]], process substitution, BASH_SOURCE),
run through Claude Code's Bash tool. Report the resolved interpreter; FAIL only if no bash is
resolvable. Pointer: for which shell a platform's sessions get, native Windows included, fetch
tools reference: PowerShell tool
live. As of: 2026-11-10. Recheck trigger: that section changes which shell a platform gets.
- Network reachability, INFO only:
audit's drift/freshness fetches read
raw.githubusercontent.com, and a failed fetch degrades to SKIP rather than a setup failure. Do not
fetch here; check performs no network call.
The audit-pass suppression record
audit-pass reads a tracked suppression record layered per the marketplace's config-cascade
convention. Read the operative shape from
${CLAUDE_PLUGIN_ROOT}/skills/audit-pass/reference/suppression.md rather than inferring it. That
reference ships inside this plugin, so it resolves in an installed cache where a path out to the
marketplace's own docs does not. The cross-consumer key contract is the marketplace's published
finding-suppression convention, which is not a runtime dependency of this plugin. All layers
absent is a valid state (no suppressions), so report INFO, never FAIL, when none exists.
Anchor at the repo root (${CLAUDE_PROJECT_DIR}, else git rev-parse --show-toplevel), never a
CWD-relative read, which resolves a different (or missing) file depending on the subdirectory or
nested worktree the skill was invoked from, then report one row per layer. The same
tracked/ignored question has opposite correct answers per layer, so verify each on its own terms:
- user-global
~/.claude/audit-pass.md: outside the worktree; no git command applies. INFO only.
- team
<home>/harness-config.yaml: must be tracked, probed as the pair:
git check-ignore -v reports no match (a match is FAIL with the pattern) AND
git ls-files --error-unmatch exits 0. Untracked while present is a hard STOP:
teammates never receive the shared suppressions. Parse it with
awk -v STRICT=1 -f ${CLAUDE_PLUGIN_ROOT}/lib/yaml-subset.awk <file>, the parser the audit engine
uses: a non-zero exit is FAIL with the line it prints, because the engine then drops the whole team
layer. The common cause is an unquoted anchor/v1 key; the parser takes a plain key only of
letters, digits, _ and -, so the key is written "anchor/v1":.
- personal override
.claude/audit-pass.local.md: must be gitignored and never staged. Staged or
tracked is a FAIL: a personal deviation can reach team history.
Parse each present layer and report as malformed any entry missing any of its five required
keys: check, claim, sites, reason, date. Checking only reason and date would pass an
entry that audit-pass itself rejects, so readiness would report green on configuration that cannot
suppress anything. Report as malformed too an entry whose stored constituents do not hash to its own
key: the constituents are authoritative and the key is derived from them. A malformed entry does not
suppress, and a silent partial parse would turn a formatting slip into a lost check.
Report a user-global or personal override entry for an id the team layer does not carry as INFO
personal-only, not applied, naming promotion to the team layer as what makes it take effect. The
team layer is the only one that enacts a suppression, so a personal-only entry that looks live is a
finding the operator believes is accepted and is not.
apply (idempotent)
Run check, then for each FAIL give the platform install instructions from the README Requirements.
This skill never installs system packages:
- missing
jq: the platform's jq install (for example winget install jqlang.jq, brew install jq, or apt-get install jq); rerun check after.
- missing
curl: the platform's curl install. Modern Windows and Git Bash already ship curl.
Only the plugin-drift check needs it, so the rest of the plugin works meanwhile.
- missing
awk or sort: both ship with every POSIX userland, so absence means the shell
environment is minimal rather than that one package is missing. Git Bash and Windows busybox
shims are where this shows up. Remediate by installing a full userland rather than the single tool:
Git for Windows, which bundles both; the distribution's gawk/mawk and coreutils on Linux;
brew install gawk coreutils on macOS. Report the two separately, since a minimal shell can carry
one and not the other. The skills check step 3 names depend on them, and only
conflict-scan.sh and instruction-scan.sh exit 2 cleanly, so do not offer the others as still
working meanwhile.
- no resolvable bash: also not remediable by one package. The scripts use arrays,
[[ ]],
process substitution, and BASH_SOURCE, so they need a real bash on PATH: Git for Windows on
native Windows, the distribution's bash elsewhere. Nothing bundled runs until it resolves, so
say that this FAIL blocks the plugin rather than offering a partial workaround.
The network row stays INFO and has no apply entry on purpose: a failed fetch degrades to SKIP by
design, so there is nothing to remediate.
After any install, re-run the relevant probe via Bash (command -v <tool>; the pre-computed rows
predate the install) and report its actual result. Never claim resolved
on the install command's exit code alone. Re-running apply once every probe passes changes nothing and
reports "already configured".
Then converge the one surface this plugin owns, conservatively:
- No suppression record anywhere: leave it that way and say so. Absent is valid; an empty
scaffold is noise. Scaffold
<home>/harness-config.yaml with the documented shape only on an
explicit request.
- Team layer present but untracked: report the STOP and the exact
git add the operator should
run. Never stage on their behalf.
- Personal override present but not ignored: recommend the recursive
.claude/**/*.local.* line and leave
the .gitignore edit to the consumer.
- Malformed or unrecognized entries: report them and stop. Never rewrite, reorder, or drop an
operator's suppression: an entry this skill cannot reconcile is a question for the operator, and a
silent rewrite would hide the very finding the entry was suppressing.
Every write names the file and the exact change before making it, and preserves unrelated content.
wsl-profile (print only)
An opt-in settings profile for Claude Code inside WSL. Read
reference/wsl-profile.md for what it holds and its limits.
- Run
bash ${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/wsl-profile.sh detect. Exit 1 means this is
not a WSL host: say the profile does not apply and stop.
- Run
bash ${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/wsl-profile.sh print. It fills in the
running user's paths and the Windows host's /mnt/<drive>/Users/<user> directories. Show the
block, relay its stderr notes (several Windows users, or placeholders left to fill in), and tell
the user to merge it into their own settings file.
- State the limit from the reference: deny rules do not stop a script that opens files itself; the
sandbox is the OS-level control.
- Name
appendWindowsPath=false in wsl.conf and the PowerShell symlink as host steps the human
runs.
This action writes no file, edits no settings and never touches wsl.conf or creates the symlink. To
check an edited profile, run ... wsl-profile.sh lint <file>.
Gotchas
- Never run a git command against the user-global layer.
~/.claude/audit-pass.md is outside the
worktree, so git check-ignore and git status return a meaningless verdict there, or a
confidently wrong one when the home directory is itself a git repository.
- Missing config is not a failure. All three suppression layers absent means no suppressions,
which is the normal state for a repo that has never suppressed a finding. INFO, never FAIL.
- Recommend the recursive gitignore line, and leave the edit to the consumer.
.claude/**/*.local.*
covers flat, folder-form, and profiled personal overrides alike; the narrower .claude/*.local.*
silently misses any nested personal override. The consumer's ignore file is their artifact; this skill never writes it.
- An install command's exit code is not verification. After any install, re-run the probe and
report its actual result.
What this skill does NOT do
- Run an audit; that is the plugin's audit and drafting skills (
/harness-config:audit,
audit-automation-gaps, audit-instructions, audit-pass, audit-permission-grants,
audit-permission-state, audit-prompting-postures, draft-auto-mode-rules, unhobble).
- Write the plugin cache, Claude Code user settings, or
pluginConfigs; wsl-profile prints a block and the user merges it.
- Install system packages.
- Write the consumer's
.gitignore, stage anything, or edit an operator's suppression entries.
- Download anything.
check makes no network call; the audit skills' own doc/marketplace fetches are
theirs, not setup's.
1---2name: setup-653description: "Verify harness-config's readiness for this repository: the external CLI prerequisites its audit scripts need, jq (the JSON-parsing audit scripts) and curl (the plugin-drift check), and the tracked suppression record in docs/conventions/harness-config.yaml, so the audit skills run instead of failing. Use when: 'set up harness-config', 'configure harness-config', 'is harness-config working', 'set up audit-pass suppressions', or an audit skill reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found) | wsl-profile (print an opt-in WSL hardening settings block, writes nothing). Re-runnable and safe."4argument-hint: "[check|apply|wsl-profile]"5user-invocable: true6disable-model-invocation: true7allowed-tools:8 - "Bash(command -v jq*)"9 - "Bash(command -v curl*)"10 - "Bash(command -v awk*)"11 - "Bash(command -v sort*)"12 - "Bash(bash ${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/wsl-profile.sh *)"13shell: bash14metadata:15 source: https://skillmd.com/skills/melodic-software/setup-6516---1718## Pre-computed context1920`check`'s tool probes ran at load time. Read these rows instead of re-issuing them; each shows the21tool's path when present, or `absent` when missing:2223- `jq`: !`command -v jq 2>/dev/null || echo absent`24- `curl`: !`command -v curl 2>/dev/null || echo absent`25- `awk`: !`command -v awk 2>/dev/null || echo absent`26- `sort`: !`command -v sort 2>/dev/null || echo absent`2728A row reading `[shell command execution disabled by policy]` carries no result: run that tool's29`command -v` probe via Bash instead.3031## Purpose3233Setup per the uniform setup contract (`docs/plugin-philosophy.md` "Setup is explicit and repeatable" in34the marketplace repository): `check` inspects and reports, `apply` resolves. This plugin declares no35`userConfig`, and has two setup concerns:3637- the external command-line tools its bundled scripts require, where `apply` is guidance-and-verify38 with no write path: it points at platform install instructions and never installs a system package;39- the **tracked consumer-project configuration** `audit` and `audit-pass` read, the `suppressions`40 mapping of `<home>/harness-config.yaml`, the one file `apply` may write. `<home>` is the41 convention home the repository binds in the pointer region of its `AGENTS.md` or `CLAUDE.md`42 (`bash ${CLAUDE_PLUGIN_ROOT}/lib/resolve-convention-home.sh` prints it), else `docs/conventions`.4344Action routing: no argument or `check` runs the check; `apply` runs the check first, then remediation;45`wsl-profile` runs only its own section. All are non-interactive, so never prompt when the action is given.4647## `check` (read-only)4849The bundled scripts are the single source of truth for what this plugin requires.5051**Read it first.** Probe what it actually does, don't recite this file. Then read the52pre-computed tool rows, run the remaining probes via Bash, and report a PASS/FAIL/INFO table with one remediation line per FAIL. Do not modify anything.5354The runtime scripts and their tools:5556- `${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/check-plugin-drift.sh`: jq **and** curl57- `${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/check-structure.sh`, `check-hook-coverage.sh` and `fix-plugin-drift.sh`: jq58- `${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/audit-engine.sh`: jq plus awk and sort; `check-effort-pins.sh`: jq plus awk59- `${CLAUDE_PLUGIN_ROOT}/skills/audit-automation-gaps/scripts/inventory.sh`: jq plus awk60- `${CLAUDE_PLUGIN_ROOT}/skills/audit-permission-grants/scripts/permission-rule-check.sh`: jq plus awk and sort61- `${CLAUDE_PLUGIN_ROOT}/skills/audit-permission-state/scripts/*.sh`: jq (required; `permission-state.sh` exits 2 without it), awk and sort; `automode-block-lint.sh` and `automode-entry-diff.sh` add python3 for an optional lane62- `${CLAUDE_PLUGIN_ROOT}/skills/draft-auto-mode-rules/scripts/draft-automode-block.sh`: jq63- `${CLAUDE_PLUGIN_ROOT}/skills/audit-pass/scripts/run-state.sh`: jq (falls back to python3, then to a scan that announces itself)64- `${CLAUDE_PLUGIN_ROOT}/lib/check-retirements.sh`: awk (no jq)65- `${CLAUDE_PLUGIN_ROOT}/skills/audit-pass/scripts/state-digest.sh` and `finding-identity.sh`: sort66- `${CLAUDE_PLUGIN_ROOT}/skills/audit-instructions/scripts/instruction-scan.sh`: grep, tr and awk (no jq)67- `${CLAUDE_PLUGIN_ROOT}/skills/audit-instructions/scripts/conflict-scan.sh`: awk **and** sort (no jq)6869Most scripts that need `jq` probe for it, but only `conflict-scan.sh` and `instruction-scan.sh` probe70for `awk` and `sort`; the rest call those with no guard, so read each script's actual calls rather than trusting a single script's prerequisite block to71speak for the plugin.72731. **`jq`**, from the pre-computed `jq` row. FAIL if absent: the JSON-parsing scripts need it (`inventory.sh` degrades74 to an empty inventory; the others `exit 2` with an install remediation). Missing `jq` blocks every75 skill whose scripts parse JSON (`audit`, `audit-automation-gaps`, `audit-permission-grants`,76 `audit-permission-state`, `draft-auto-mode-rules`, and `audit-pass`'s run-state helper); `audit-instructions` scans markdown and is unaffected.772. **`curl`**, from the pre-computed `curl` row. FAIL if absent, but scoped: only the plugin-drift check78 (`check-plugin-drift.sh`) uses it and `exit 2`s without it. The rest of `audit` and every other79 skill still run; say so in the remediation line.803. **`awk` and `sort`**, from the pre-computed `awk` and `sort` rows. FAIL if either is absent, and **not**81 scoped to one skill: `conflict-scan.sh` and `instruction-scan.sh` probe and `exit 2` naming the82 missing one, while the other scripts in the list above that use them have no prerequisite check83 at all, so their skills fail mid-run on a bare `command not found` rather than on a named84 prerequisite. Say in the85 remediation line that this FAIL reaches six skills (`audit`, `audit-automation-gaps`,86 `audit-pass`, `audit-permission-grants`, `audit-permission-state` and `audit-instructions`), not87 just `audit-instructions`. Report `awk` and `sort` by name rather than as one row, since a88 minimal shell can carry one and not the other.894. **Bash shell**, INFO: the scripts are bash (arrays, `[[ ]]`, process substitution, `BASH_SOURCE`),90 run through Claude Code's Bash tool. Report the resolved interpreter; FAIL only if no bash is91 resolvable. Pointer: for which shell a platform's sessions get, native Windows included, fetch92 [tools reference: PowerShell tool](https://code.claude.com/docs/en/tools-reference#powershell-tool)93 live. As of: 2026-11-10. Recheck trigger: that section changes which shell a platform gets.945. **Network reachability**, INFO only: `audit`'s drift/freshness fetches read95 `raw.githubusercontent.com`, and a failed fetch degrades to SKIP rather than a setup failure. Do not96 fetch here; `check` performs no network call.9798### The `audit-pass` suppression record99100`audit-pass` reads a tracked suppression record layered per the marketplace's config-cascade101convention. Read the operative shape from102`${CLAUDE_PLUGIN_ROOT}/skills/audit-pass/reference/suppression.md` rather than inferring it. That103reference ships inside this plugin, so it resolves in an installed cache where a path out to the104marketplace's own docs does not. The cross-consumer key contract is the marketplace's published105**finding-suppression** convention, which is not a runtime dependency of this plugin. All layers106absent is a valid state (no suppressions), so report INFO, never FAIL, when none exists.107108Anchor at the repo root (`${CLAUDE_PROJECT_DIR}`, else `git rev-parse --show-toplevel`), never a109CWD-relative read, which resolves a different (or missing) file depending on the subdirectory or110nested worktree the skill was invoked from, then report one row per layer. The same111tracked/ignored question has opposite correct answers per layer, so verify each on its own terms:112113- **user-global** `~/.claude/audit-pass.md`: outside the worktree; no git command applies. INFO only.114- **team** `<home>/harness-config.yaml`: must be tracked, probed as the pair:115 `git check-ignore -v` reports no match (a match is FAIL with the pattern) AND116 `git ls-files --error-unmatch` exits 0. Untracked while present is a hard STOP:117 teammates never receive the shared suppressions. Parse it with118 `awk -v STRICT=1 -f ${CLAUDE_PLUGIN_ROOT}/lib/yaml-subset.awk <file>`, the parser the audit engine119 uses: a non-zero exit is FAIL with the line it prints, because the engine then drops the whole team120 layer. The common cause is an unquoted `anchor/v1` key; the parser takes a plain key only of121 letters, digits, `_` and `-`, so the key is written `"anchor/v1":`.122- **personal override** `.claude/audit-pass.local.md`: must be gitignored and never staged. Staged or123 tracked is a FAIL: a personal deviation can reach team history.124125Parse each present layer and report as malformed any entry missing **any** of its five required126keys: `check`, `claim`, `sites`, `reason`, `date`. Checking only `reason` and `date` would pass an127entry that `audit-pass` itself rejects, so readiness would report green on configuration that cannot128suppress anything. Report as malformed too an entry whose stored constituents do not hash to its own129key: the constituents are authoritative and the key is derived from them. A malformed entry does not130suppress, and a silent partial parse would turn a formatting slip into a lost check.131132Report a **user-global or personal override entry for an id the team layer does not carry** as INFO133`personal-only, not applied`, naming promotion to the team layer as what makes it take effect. The134team layer is the only one that enacts a suppression, so a personal-only entry that looks live is a135finding the operator believes is accepted and is not.136137## `apply` (idempotent)138139Run `check`, then for each FAIL give the platform install instructions from the README Requirements.140This skill never installs system packages:141142- **missing `jq`:** the platform's jq install (for example `winget install jqlang.jq`, `brew install143 jq`, or `apt-get install jq`); rerun `check` after.144- **missing `curl`:** the platform's curl install. Modern Windows and Git Bash already ship `curl`.145 Only the plugin-drift check needs it, so the rest of the plugin works meanwhile.146- **missing `awk` or `sort`:** both ship with every POSIX userland, so absence means the shell147 environment is minimal rather than that one package is missing. Git Bash and Windows `busybox`148 shims are where this shows up. Remediate by installing a full userland rather than the single tool:149 Git for Windows, which bundles both; the distribution's `gawk`/`mawk` and `coreutils` on Linux;150 `brew install gawk coreutils` on macOS. Report the two separately, since a minimal shell can carry151 one and not the other. The skills `check` step 3 names depend on them, and only152 `conflict-scan.sh` and `instruction-scan.sh` `exit 2` cleanly, so do not offer the others as still153 working meanwhile.154- **no resolvable bash:** also not remediable by one package. The scripts use arrays, `[[ ]]`,155 process substitution, and `BASH_SOURCE`, so they need a real bash on `PATH`: Git for Windows on156 native Windows, the distribution's `bash` elsewhere. Nothing bundled runs until it resolves, so157 say that this FAIL blocks the plugin rather than offering a partial workaround.158159The network row stays INFO and has no `apply` entry on purpose: a failed fetch degrades to SKIP by160design, so there is nothing to remediate.161162After any install, re-run the relevant probe via Bash (`command -v <tool>`; the pre-computed rows163predate the install) and report its actual result. Never claim resolved164on the install command's exit code alone. Re-running `apply` once every probe passes changes nothing and165reports "already configured".166167Then converge the one surface this plugin owns, conservatively:168169- **No suppression record anywhere**: leave it that way and say so. Absent is valid; an empty170 scaffold is noise. Scaffold `<home>/harness-config.yaml` with the documented shape only on an171 explicit request.172- **Team layer present but untracked**: report the STOP and the exact `git add` the operator should173 run. Never stage on their behalf.174- **Personal override present but not ignored**: recommend the recursive `.claude/**/*.local.*` line and leave175 the `.gitignore` edit to the consumer.176- **Malformed or unrecognized entries**: report them and stop. Never rewrite, reorder, or drop an177 operator's suppression: an entry this skill cannot reconcile is a question for the operator, and a178 silent rewrite would hide the very finding the entry was suppressing.179180Every write names the file and the exact change before making it, and preserves unrelated content.181182## `wsl-profile` (print only)183184An opt-in settings profile for Claude Code inside WSL. Read185[reference/wsl-profile.md](reference/wsl-profile.md) for what it holds and its limits.1861871. Run `bash ${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/wsl-profile.sh detect`. Exit 1 means this is188 not a WSL host: say the profile does not apply and stop.1892. Run `bash ${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/wsl-profile.sh print`. It fills in the190 running user's paths and the Windows host's `/mnt/<drive>/Users/<user>` directories. Show the191 block, relay its stderr notes (several Windows users, or placeholders left to fill in), and tell192 the user to merge it into their own settings file.1933. State the limit from the reference: deny rules do not stop a script that opens files itself; the194 sandbox is the OS-level control.1954. Name `appendWindowsPath=false` in `wsl.conf` and the PowerShell symlink as host steps the human196 runs.197198This action writes no file, edits no settings and never touches `wsl.conf` or creates the symlink. To199check an edited profile, run `... wsl-profile.sh lint <file>`.200201## Gotchas202203- **Never run a git command against the user-global layer.** `~/.claude/audit-pass.md` is outside the204 worktree, so `git check-ignore` and `git status` return a meaningless verdict there, or a205 confidently wrong one when the home directory is itself a git repository.206- **Missing config is not a failure.** All three suppression layers absent means no suppressions,207 which is the normal state for a repo that has never suppressed a finding. INFO, never FAIL.208- **Recommend the recursive gitignore line, and leave the edit to the consumer.** `.claude/**/*.local.*`209 covers flat, folder-form, and profiled personal overrides alike; the narrower `.claude/*.local.*`210 silently misses any nested personal override. The consumer's ignore file is their artifact; this skill never writes it.211- **An install command's exit code is not verification.** After any install, re-run the probe and212 report its actual result.213214## What this skill does NOT do215216- Run an audit; that is the plugin's audit and drafting skills (`/harness-config:audit`,217 `audit-automation-gaps`, `audit-instructions`, `audit-pass`, `audit-permission-grants`,218 `audit-permission-state`, `audit-prompting-postures`, `draft-auto-mode-rules`, `unhobble`).219- Write the plugin cache, Claude Code user settings, or `pluginConfigs`; `wsl-profile` prints a block and the user merges it.220- Install system packages.221- Write the consumer's `.gitignore`, stage anything, or edit an operator's suppression entries.222- Download anything. `check` makes no network call; the audit skills' own doc/marketplace fetches are223 theirs, not setup's.