/quickstart
Two modes, picked by whether $ARGUMENTS is empty.
- Empty → Intro mode. Short orientation, then offer the guided first run.
- Non-empty → Help mode. Treat
$ARGUMENTS as the operator's question.
Intro mode
Keep it short and a little warm; this is the first thing a new operator sees.
Say roughly:
Welcome! This repo takes you from finding your first vulnerability to
patching at scale, using a set of Claude Code skills and an autonomous
pipeline. Two ways in: interactive skills (no setup, safe, start here)
and the autonomous pipeline (Docker, scales to hundreds of parallel
agents).
The ramp-up:
| Day 1 | Threat-model + first static scan + triage |
| Day 2 | Run the reference pipeline (C/C++) |
| Day 3-4 | Customize it for your stack |
| Week 2 | Autonomous scanning, triage, and patching |
Day-1 goal: threat-model, scan, and triage the bundled canary target.
Most teams get there before lunch.
Remind them to export CLAUDE_CODE_SUBAGENT_MODEL=<model-id> so subagents
use the same model as the session.
Then AskUserQuestion with three options:
- Walk me through Day 1 on the canary (~10 min) → run "Guided first
run" below.
- I have a question → ask what it is, then switch to Help mode.
- I'll read the README → point at
README.md Step 1 and stop.
Guided first run
Runs the three Step-1 skills on targets/canary, pausing after each to show
what landed on disk. These only read/write files in the repo; no sandbox
needed.
/threat-model bootstrap targets/canary via Task. When done, open
THREAT_MODEL.md, show the focus areas, explain in 2-3 sentences how
this steers the scan.
/vuln-scan targets/canary via Task. When done, open
targets/canary/VULN-FINDINGS.md, summarize the count and top 2-3
findings, point at VULN-FINDINGS.json.
/triage targets/canary/VULN-FINDINGS.json via Task. When done, open
TRIAGE.md, explain what changed vs. raw findings (verified, deduped,
re-ranked).
Pause for the operator between each (AskUserQuestion); don't barrel through.
Close with a one-line recap of the three artifacts on disk, then point at
README Step 2 for the execution-verified pipeline. Never run vuln-pipeline
or anything that executes target code here; that's Step 2 and needs
Docker + a sandbox.
Help mode
Answer the operator's question using this repo as ground truth: README,
docs/*.md, harness/*.py, dnr_harness/*.py, targets/*/config.yaml,
.claude/skills/*.
Don't answer from general knowledge when the repo has a specific answer.
Routing map
| If the question is about… |
Read first |
Then offer |
| running the pipeline |
docs/pipeline.md, README Step 2 |
the recon / run command |
| too many findings, triage |
docs/triage.md |
/triage <path> |
| porting, Java/Go/Rust/etc. |
docs/customizing.md, README Step 3 |
/customize |
| safety, sandbox, Docker |
docs/security.md |
cite; no action |
| rate limits, 429, token budget |
docs/pipeline.md: Rate limits, docs/troubleshooting.md#rate-limits |
cite the numbers |
| duplicates, dedup |
docs/troubleshooting.md#duplicate-findings |
known_bugs: hint |
| CLI flags, "what does --X do" |
harness/cli.py (grep the argparse) |
exact flag + example |
| which model, subagent pinning |
docs/troubleshooting.md: Subagents |
the export line |
| best practices, prompting |
docs/best-practices.md, docs/prompting.md |
cite the principle |
| threat model, attack surface, scope |
docs/threat-model.md |
/threat-model bootstrap <target-dir> |
| scan, audit, find vulns |
.claude/skills/vuln-scan/SKILL.md |
/vuln-scan <target-dir> |
| "how do I start" |
README Step 1 |
offer Guided first run |
| patching, fix, diff, re-attack |
docs/patching.md, README Step 4 |
/patch <input> |
| threat hunting, incident response, logs |
docs/detection-response.md |
/dnr-hunt or /dnr-respond |
| autonomous D&R, dnrcanary |
docs/detection-response.md, targets/dnrcanary/README.md |
the dnr-pipeline run command |
| binary, embedded, other domains |
docs/other-use-cases.md |
cite section |
| anything else |
README Table of contents |
best-match doc |
Answer format
- Direct answer in 2-5 sentences.
> source: the file(s) and section you used.
- Next action: one copy-pasteable command or skill invocation, if one
applies. If none does, say so.
- If the question is ambiguous, ask one clarifying question; don't guess.
Constraints
- Never fabricate CLI flags or file paths. If unsure,
Grep for it in
harness/cli.py or the target configs and quote what you find.
- If the repo doesn't answer the question, say so plainly and suggest the
operator open a GitHub issue on this repo.
- Keep the Q&A dry and cited. Save the warmth for Intro mode.
1---
2name: quickstart
3description: >-
4 The front door for this repo. With no argument: a 30-second
5 intro, then an offer to walk you through your first run on the canary
6 target. With a question: answers it from this repo's own docs and source,
7 cites where it looked, and hands you the next command. Use for "how do
8 I…", "why does…", "where is…", "can this…", or just "/quickstart" to get
9 oriented.
10argument-hint: "[question] (blank = 30-sec intro)"
11allowed-tools:
12 - Read
13 - Glob
14 - Grep
15 - Task
16 - AskUserQuestion
17metadata:
18 source: https://skillmd.com/skills/anthropics/quickstart
19---
20
21# /quickstart
22
23Two modes, picked by whether `$ARGUMENTS` is empty.
24
25- **Empty → Intro mode.** Short orientation, then offer the guided first run.
26- **Non-empty → Help mode.** Treat `$ARGUMENTS` as the operator's question.
27
28---
29
30## Intro mode
31
32Keep it short and a little warm; this is the first thing a new operator sees.
33
34Say roughly:
35
36> **Welcome!** This repo takes you from finding your first vulnerability to
37> patching at scale, using a set of Claude Code skills and an autonomous
38> pipeline. Two ways in: **interactive skills** (no setup, safe, start here)
39> and the **autonomous pipeline** (Docker, scales to hundreds of parallel
40> agents).
41>
42> The ramp-up:
43>
44> | Day 1 | Threat-model + first static scan + triage |
45> | Day 2 | Run the reference pipeline (C/C++) |
46> | Day 3-4 | Customize it for your stack |
47> | Week 2 | Autonomous scanning, triage, and patching |
48>
49> Day-1 goal: threat-model, scan, and triage the bundled canary target.
50> Most teams get there before lunch.
51
52Remind them to `export CLAUDE_CODE_SUBAGENT_MODEL=<model-id>` so subagents
53use the same model as the session.
54
55Then **AskUserQuestion** with three options:
56
571. **Walk me through Day 1 on the canary (~10 min)** → run "Guided first
58 run" below.
592. **I have a question** → ask what it is, then switch to Help mode.
603. **I'll read the README** → point at `README.md` Step 1 and stop.
61
62### Guided first run
63
64Runs the three Step-1 skills on `targets/canary`, pausing after each to show
65what landed on disk. These only read/write files in the repo; no sandbox
66needed.
67
681. `/threat-model bootstrap targets/canary` via Task. When done, open
69 `THREAT_MODEL.md`, show the focus areas, explain in 2-3 sentences how
70 this steers the scan.
712. `/vuln-scan targets/canary` via Task. When done, open
72 `targets/canary/VULN-FINDINGS.md`, summarize the count and top 2-3
73 findings, point at `VULN-FINDINGS.json`.
743. `/triage targets/canary/VULN-FINDINGS.json` via Task. When done, open
75 `TRIAGE.md`, explain what changed vs. raw findings (verified, deduped,
76 re-ranked).
77
78Pause for the operator between each (AskUserQuestion); don't barrel through.
79Close with a one-line recap of the three artifacts on disk, then point at
80README Step 2 for the execution-verified pipeline. **Never run `vuln-pipeline`
81or anything that executes target code here**; that's Step 2 and needs
82Docker + a sandbox.
83
84---
85
86## Help mode
87
88Answer the operator's question using **this repo as ground truth**: README,
89`docs/*.md`, `harness/*.py`, `dnr_harness/*.py`, `targets/*/config.yaml`,
90`.claude/skills/*`.
91Don't answer from general knowledge when the repo has a specific answer.
92
93### Routing map
94
95| If the question is about… | Read first | Then offer |
96|---------------------------------|-----------------------------------------|------------|
97| running the pipeline | `docs/pipeline.md`, README Step 2 | the `recon` / `run` command |
98| too many findings, triage | `docs/triage.md` | `/triage <path>` |
99| porting, Java/Go/Rust/etc. | `docs/customizing.md`, README Step 3 | `/customize` |
100| safety, sandbox, Docker | `docs/security.md` | cite; no action |
101| rate limits, 429, token budget | `docs/pipeline.md`: Rate limits, `docs/troubleshooting.md#rate-limits` | cite the numbers |
102| duplicates, dedup | `docs/troubleshooting.md#duplicate-findings` | `known_bugs:` hint |
103| CLI flags, "what does --X do" | `harness/cli.py` (grep the argparse) | exact flag + example |
104| which model, subagent pinning | `docs/troubleshooting.md`: Subagents | the `export` line |
105| best practices, prompting | `docs/best-practices.md`, `docs/prompting.md` | cite the principle |
106| threat model, attack surface, scope | `docs/threat-model.md` | `/threat-model bootstrap <target-dir>` |
107| scan, audit, find vulns | `.claude/skills/vuln-scan/SKILL.md` | `/vuln-scan <target-dir>` |
108| "how do I start" | README Step 1 | offer Guided first run |
109| patching, fix, diff, re-attack | `docs/patching.md`, README Step 4 | `/patch <input>` |
110| threat hunting, incident response, logs | `docs/detection-response.md` | `/dnr-hunt` or `/dnr-respond` |
111| autonomous D&R, dnrcanary | `docs/detection-response.md`, `targets/dnrcanary/README.md` | the `dnr-pipeline run` command |
112| binary, embedded, other domains | `docs/other-use-cases.md` | cite section |
113| anything else | README Table of contents | best-match doc |
114
115### Answer format
116
1171. **Direct answer** in 2-5 sentences.
1182. `> source:` the file(s) and section you used.
1193. **Next action:** one copy-pasteable command or skill invocation, if one
120 applies. If none does, say so.
1214. If the question is ambiguous, ask **one** clarifying question; don't guess.
122
123### Constraints
124
125- Never fabricate CLI flags or file paths. If unsure, `Grep` for it in
126 `harness/cli.py` or the target configs and quote what you find.
127- If the repo doesn't answer the question, say so plainly and suggest the
128 operator open a GitHub issue on this repo.
129- Keep the Q&A dry and cited. Save the warmth for Intro mode.