Borrowing it
Nothing to install: this file belongs to jakubsuplicki/codument. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jakubsuplicki/codument/main/.agents/skills/update-docs/SKILL.mdgit clone --depth 1 https://github.com/jakubsuplicki/codumentWrote 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/skills/jakubsuplicki/codument/update-docs)<a href="https://agentmods.dev/skills/jakubsuplicki/codument/update-docs"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/update-docs/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/skills/jakubsuplicki/codument/update-docs"><img src="https://agentmods.dev/badge/skills/jakubsuplicki/codument/update-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.03509 |
| Opus 5.5 | $0.00025 | $0.01404 |
| Sonnet 5.5 | $0.00013 | $0.00702 |
| Haiku 4.5 | $0.00006 | $0.00351 |
Grade A, and why
update-docs 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Workflow
How to Document
You are writing documentation that another developer will read to understand this project. Your goal is to explain why things exist and how they fit together — not to restate what the code already says.
What good documentation looks like
Follow the documentation standard (the doc-audience-layers concept) — these are its layers, and the test for every line is "would this survive a refactor that renamed every symbol and reordered every line?":
- In plain terms: 2-3 sentences a reader takes in 10 seconds to know if this is relevant to them. No jargon.
- Design approach: why it is shaped this way — the forces and the chosen-vs-rejected approach, at role level. No identifiers, counts, or call order; that is mechanism, it drifts, and the agent reads it live from the code.
- Invariants & boundaries: what must always hold or is forbidden — the landmines a reader cannot see in the local code, and what the feature deliberately does NOT do. Link each invariant to the test that enforces it, or mark it "untested". This is consistently the most valuable section.
- Decisions: pointers to the ADRs that hold the durable why. Reference, never restate.
- Key files: each file's one-line narrative role (orchestrator / analyzer / seam) — not its exports. The registry holds the exact file list.
What bad documentation looks like — do NOT write this
- Restating function names as descriptions ("readRegistry reads the registry")
- Listing exports without explaining what they're for
- Copy-pasting large code blocks instead of referencing file paths
- Revision history, glossaries, or timeline sections
- Vague descriptions ("handles X logic for the application")
Start from codument doctor
Before writing anything, find out what actually needs work — don't guess. codument doctor is the deterministic gap list; let its findings (warnings) drive the pass, and re-run it after each fix so you can watch the finding clear. A finding that re-runs clean is the done signal — there is no separate sign-off.
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 · 220 lines · 63 tokens per session scan A 55407cdc5259
update-docs is a skill published in the GitHub repository jakubsuplicki/codument (48 stars, last pushed 23d ago), licensed Apache-2.0. It adds 63 tokens to every session and 3,509 once invoked, about $0.0003 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 skills, from other repositories
handoff
Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts" or "pick up".
sw-do
Work a SpecWeave increment task by task - claim, implement inside its Files, test, commit, done with evidence - alone, unattended or in lanes, then close. Use for "implement", "next task".
review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
done
Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".
sw-done
Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".
glossary
Build the shared language - interview the user term by term and write GLOSSARY.md with what each term means in the business, the data, the code and the UI. Use for "glossary", "ubiquitous language".