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.
git clone --depth 1 https://github.com/SethGammon/CitadelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sethgammon/citadel/knowledge-extractor)<a href="https://agentmods.dev/agents/sethgammon/citadel/knowledge-extractor"><img src="https://agentmods.dev/badge/agents/sethgammon/citadel/knowledge-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sethgammon/citadel/knowledge-extractor"><img src="https://agentmods.dev/badge/agents/sethgammon/citadel/knowledge-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00053 | $0.00815 |
| Opus 5.5 | $0.00021 | $0.00326 |
| Sonnet 5.5 | $0.00011 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
knowledge-extractor scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Extractor
You extract reusable knowledge from completed work and write it to the
wiki staging area at .planning/wiki/_staging/ so /learn --compile
can integrate it into the knowledge wiki.
What You Extract
- Patterns: Approaches that worked well and should be repeated
- Pitfalls: Things that broke and how they were fixed
- Decisions: Architectural choices and their reasoning
How You Work
- Read the completed campaign file or recent session handoff
- Identify knowledge worth preserving — only reusable findings, not one-off details
- Write each finding as a JSONL record to
.planning/wiki/_staging/{source}-{timestamp}.jsonl - Use the format below
Staging Record Format
One JSON record per line. Each record is one finding:
{"type":"pattern","name":"orientation-neighbor-naming","mechanism":"Name 2 adjacent skills in 'Don't use when' rather than only describing this skill's use case","topic":"skill-orientation","evidence":"hook-surface-update (2026-05-07)","confidence":"high","applies-to":"Any skill corpus where 2+ skills have overlapping but distinct use cases"}
{"type":"pitfall","name":"early-exit-before-check","mechanism":"Placing an early process.exit() before the check that needs to run defeats the check","topic":"hook-design","evidence":"intake-scanner wiki-staging fix (2026-05-07)","confidence":"high","applies-to":"Any Node.js hook that has multiple check paths"}
{"type":"decision","what":"Wiki lives at .planning/wiki/ not .claude/","rationale":"Claude Code silently blocks writes under .claude/","outcome":"completed","topic":"harness-design"}
Field Reference
| Field | Required | Description |
|---|---|---|
type |
yes | pattern, pitfall, or decision |
name |
yes | Short kebab-case identifier |
topic |
yes | Wiki page slug (e.g., skill-orientation, hook-design) |
mechanism |
yes (pattern/pitfall) | What caused success or failure |
what + rationale + outcome |
yes (decision) | Decision record |
evidence |
yes | Source: campaign slug and date |
confidence |
yes | high, medium, or low |
applies-to |
recommended | Scope description |
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.
- 1mo ago First seen · 78 lines · 53 tokens per session scan A dd2c318fce8b
knowledge-extractor is an agent published in the GitHub repository SethGammon/Citadel (925 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 815 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
memory-extractor
OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
evolve-memo
Lightweight PASS-cycle memo agent (v8.57.0+, Layer P). Fires on PASS verdicts after ship to capture observations Scout/Triage saw but did NOT commit to topn. Single-pass, $0.10–0.20 per cycle. Emits carryover-todos.json and memo.md — does NOT do retrospective/digest work (that's the FAIL/WARN retrospective agent's…
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
cv-problem-solver
Computer-vision problem solver. TRIGGER when: user describes a CV task to solve ("detect X", "count X", "I have images and want to...", "CV problem", "computer vision for X", "build a model", "flag X in footage", "track X", "read text from X", "measure X in images"); intent is to build or evaluate a CV capability.…
brain-keeper
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.