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/everywan-dev/claude-code-engineering/map-an-undocumented-systemnpx skills add everywan-dev/claude-code-engineering --skill map-an-undocumented-systemgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWhat 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 | $0.00036 | $0.01833 |
| Opus 5 | $0.00018 | $0.00916 |
| Sonnet 5 | $0.00007 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
map-an-undocumented-system 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 2d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Map an undocumented system
A body of documentation that only states what it knows produces a specific, expensive illusion:
Everything not written down is either unimportant or does not exist.
Neither is true. What is not written down is usually the part nobody understood well enough to write. The gaps are not the leftovers of the documentation effort — they are its most actionable output.
So record them. Deliberately, in the repository, with the same care as the facts.
When to use this
- Documenting a system for the first time
- Migrating loose notes into a structured knowledge base
- Onboarding onto something someone else built
- Answering "what do we actually know here?" before a risky change
- Any time you catch yourself writing "presumably" or "I assume this is"
The procedure
1. Give the gaps a home
A list of unknowns kept in your head, or in a session that ends, is not a map. It needs a file that lives with the documentation and is read at the same time.
2. Write each gap as a question, not as a feeling
🔴 If you cannot phrase it as a question with a possible answer, it is not a gap — it is unease. Unease belongs in prose; gaps belong in the list.
| Not a gap | A gap |
|---|---|
| "The networking side is murky" | "Which component terminates inbound connections before they reach the application?" |
| "Storage worries me" | "What is the retention policy on the archive volume, and who set it?" |
| "Nobody understands the scheduler" | "What triggers the nightly run, and where is its schedule defined?" |
3. Say what the gap blocks
A gap with no consequence attached will never be closed, and should not be. Write the decision that is waiting on it: "blocks: whether this can be restarted during business hours."
Gaps that block nothing go in a low-priority section, or nowhere. A gap list that grows without bound stops being read, which makes it worse than no list.
4. Prove the gap — searching and not finding is the evidence
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.
- 2d ago First seen · 187 lines · 36 tokens per session scan A b0ce048ab979
map-an-undocumented-system is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,833 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
claude-project-manifest
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
proofpress
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
PBE Extractor
Extract invariant principles from any text — find the ideas that survive rephrasing.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.
golden-rss
Use when testing the rss golden build.