Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/sethgammon/citadel/verifynpx skills add SethGammon/Citadel --skill verifygit clone --depth 1 https://github.com/SethGammon/CitadelWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.01138 |
| Opus 5 | $0.00030 | $0.00569 |
| Sonnet 5 | $0.00012 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade B, and why
verify scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
→ Check settings.json: cat .claude/settings.json | grep PostToolUse How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify — Hook Pipeline Self-Test
Use this when:
- Hooks were recently updated and you want a live sanity check
- Something feels wrong (tools seem too slow, quality-gate not firing)
- After installing Citadel in a new project
Protocol
Step 1: Baseline
Read the current telemetry state:
.planning/telemetry/hook-timing.jsonl → count lines (baseline_timing)
.planning/telemetry/audit.jsonl → count lines (baseline_audit)
.planning/telemetry/hook-errors.log → size in bytes (baseline_errors)
If telemetry directory doesn't exist, note it (init-project may not have run).
Step 2: Exercise hooks
Run these tool calls in sequence. Each exercises a different hook:
-
Write a temp file at
.planning/verify-temp.ts:// citadel verify probe export const verifyProbe = true;→ Exercises: PreToolUse (protect-files, governance), PostToolUse (post-edit)
-
Edit the same file — change
truetofalse: → Exercises: PreToolUse (protect-files, governance), PostToolUse (post-edit) -
Bash a harmless read command:
echo "verify-probe"→ Exercises: PreToolUse (governance) -
Read the temp file back → Exercises: PreToolUse (protect-files — should allow, it's not .env)
-
Delete the temp file:
rm .planning/verify-temp.tsor equivalent → Cleanup
Step 3: Check side effects
After all tool calls complete, read telemetry again:
| Check | Expected | Result |
|---|---|---|
| hook-timing.jsonl grew | +2 or more lines (Write + Edit post-hooks) | PASS/FAIL |
| audit.jsonl grew | +3 or more lines (Write + Edit + Bash pre-hooks) | PASS/FAIL |
| hook-errors.log unchanged | same size as baseline | PASS/FAIL |
Step 4: Report
Output a results block:
=== HOOK HEALTH CHECK ===
hook-timing.jsonl: +N lines [PASS / FAIL]
audit.jsonl: +N lines [PASS / FAIL]
hook-errors.log: no errors [PASS / FAIL — N new errors]
HOOK HEALTH: PASS
Or if any check fails:
HOOK HEALTH: FAIL
Failing checks:
- hook-timing.jsonl did not grow: PostToolUse hooks may not be firing
→ Verify hooks are installed: node scripts/verify-hooks.js
→ Check settings.json: cat .claude/settings.json | grep PostToolUse
- audit.jsonl did not grow: governance hook may not be firing
→ Check: node hooks_src/governance.js <<< '{}'
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 144 lines · 60 tokens per session scan B dd52b53b4120
verify is a skill published in the GitHub repository SethGammon/Citadel (914 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 1,138 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debrief
This skill should be used when the user asks to "debrief", "record what happened", "session summary", "write a debrief", or wants to capture session activity (commits, task state changes, decisions, issues) into a structured record for the next session.
refit
This skill should be used when the user asks to "refit a workflow", "upgrade a workflow", "update workflow scaffolding", or wants to bring an existing workflow's scaffolding files up to date with the current Spacedock version.
fo-dispatch-recovery
Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual Agent() template) and Context Budget Failure/Dead Ensign Handling (the budget-unavailable stderr conditions, the recovery clause, dead-ensign bookkeeping). Read ONLY at its resident triggers inside claude-fo-dispatch.md — a non-zero or…
fo-status-viewer
First-officer status query/mutate/display surface — the status command flag docs, --set field docs, canonical captain-facing invocations, the Captain-Facing State Display rendering, and the GitHub-issue-filing approval gate. Invoke at the first ad-hoc status question, --set mutation, --next-id/--resolve lookup, or…
present-gate
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.
agent-workflow-playbook
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…