How do I install the Campaign Health skill?

Run npx skillmds@latest add encod3d-sec/campaign-health in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Campaign Health safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Campaign Health?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Campaign Health free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Campaign Health?

Encod3d-Sec (@encod3d-sec) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Campaign Health by encod3d-sec — Agent Skill

Name: Campaign Health
Author: Encod3d-Sec

Campaign Health

Health check for the bb/pt/ctf workflow driver subsystem - verifies everything is in place so every machine runs the same. Checks vault-content consistency (scripts present, JSON valid, routing wired, all 69 tool pages carry phase:, the tool index resolves, the hook edits are in place) AND per-machine wiring (the three workflow skills symlinked, hooks registered, imports work), then runs a live init->board->next smoke test. Use when setting up the workflow on a new machine, after a vault sync, when the driver misbehaves, or on "bb-health", "campaign health", "is the workflow set up", "check hooks and scripts", "why is the board not working".

Encod3d-Sec Updated Sep 21, 2026

File contents

campaign-health

The vault syncs across machines; ~/.claude (hook registration, skill symlinks, deps) does not. So "it works here" does not mean "it works there". This skill confirms both halves before you rely on bb-workflow / pt-workflow / ctf-workflow on this machine.

Run it

python3 scripts/campaign-doctor.py            # summary (only WARN/FAIL shown)
python3 scripts/campaign-doctor.py --verbose   # every check

Exit 0 = all green. Exit 1 = at least one FAIL; the driver will not run correctly here until fixed.

What it checks

A. vault content - the driver's scripts exist, every campaign JSON is valid, each type's approach exists in playbook.json and coverage-classes.json, the two hook edits (recon-capture emits spec['tools'], tool-telemetry logs binaries) are present, all 69 wiki/tools/ pages carry phase:, and campaign.tool_index() resolves an invocation for every tool.
B. machine wiring - the three workflow skills are authored and symlinked into ~/.claude/skills, hooks are registered (via check-hooks.py), and _engagement imports.
C. live smoke test - init -> board -> next against a throwaway copy of the fixture, asserting the board writes rows and next withholds the exploit at G1.

Fixing what it reports

WARN (machine wiring) - usually one setup script the doctor names: bash setup/install-skills.sh (skills) or bash setup/install-hooks.sh (hooks).
FAIL (vault content) - a stale sync or a partial edit. Re-pull the vault; if a tool page lost its phase:, re-run python3 scripts/tool-phase-backfill.py --write.

Run this first on any new machine, and after every vault sync, so all machines run the same driver.

---name: campaign-healthdescription: Health check for the bb/pt/ctf workflow driver subsystem - verifies everything is in place so every machine runs the same. Checks vault-content consistency (scripts present, JSON valid, routing wired, all 69 tool pages carry phase:, the tool index resolves, the hook edits are in place) AND per-machine wiring (the three workflow skills symlinked, hooks registered, imports work), then runs a live init->board->next smoke test. Use when setting up the workflow on a new machine, after a vault sync, when the driver misbehaves, or on "bb-health", "campaign health", "is the workflow set up", "check hooks and scripts", "why is the board not working".---# campaign-healthThe vault syncs across machines; `~/.claude` (hook registration, skill symlinks, deps) does **not**.So "it works here" does not mean "it works there". This skill confirms both halves before you rely on`bb-workflow` / `pt-workflow` / `ctf-workflow` on this machine.## Run it```python3 scripts/campaign-doctor.py # summary (only WARN/FAIL shown)python3 scripts/campaign-doctor.py --verbose # every check```Exit 0 = all green. Exit 1 = at least one FAIL; the driver will not run correctly here until fixed.## What it checks- **A. vault content** - the driver's scripts exist, every campaign JSON is valid, each type's `approach` exists in `playbook.json` and `coverage-classes.json`, the two hook edits (recon-capture emits `spec['tools']`, tool-telemetry logs binaries) are present, all 69 `wiki/tools/` pages carry `phase:`, and `campaign.tool_index()` resolves an invocation for every tool.- **B. machine wiring** - the three workflow skills are authored and symlinked into `~/.claude/skills`, hooks are registered (via `check-hooks.py`), and `_engagement` imports.- **C. live smoke test** - `init -> board -> next` against a throwaway copy of the fixture, asserting the board writes rows and `next` withholds the exploit at G1.## Fixing what it reports- **WARN (machine wiring)** - usually one setup script the doctor names: `bash setup/install-skills.sh` (skills) or `bash setup/install-hooks.sh` (hooks).- **FAIL (vault content)** - a stale sync or a partial edit. Re-pull the vault; if a tool page lost its `phase:`, re-run `python3 scripts/tool-phase-backfill.py --write`.Run this first on any new machine, and after every vault sync, so all machines run the same driver.

Frequently asked questions