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/ric03uec/clawrium/docs-syncnpx skills add ric03uec/clawrium --skill docs-syncgit clone --depth 1 https://github.com/ric03uec/clawriumWhat 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 | $0.00027 | $0.00662 |
| Opus 5 | $0.00014 | $0.00331 |
| Sonnet 5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
docs-sync 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-sync
Once per day, find code changes that altered user-visible behavior and
propose corresponding updates to docs/ and scenarios/. The goal is
that anyone running the documented commands or following the scenarios
hits the same surface real users hit today.
Inputs
git log --since='24 hours ago' --first-parent mainfor the commit set (first-parent skips merge-squash internals when present).git diff <prev>..<head>per logical change.- The current state of
docs/andscenarios/.
Triage rule — what counts as "user-visible"
Include a change in scope when any of the following is true:
- Adds, renames, removes, or changes the signature of a
clawctlCLI command or option (src/clawrium/cli/). - Changes a documented config path or env var.
- Changes an installation, configuration, or onboarding stage.
- Changes a GUI route, control, or visible label.
- Changes output of a
clawctl ps-style status command in a way a user would notice.
Exclude pure refactors, test-only changes, dependency bumps that do not change observable behavior, and internal log strings.
Output
For each cluster of related changes, open one PR titled:
docs(<area>): sync with <one-line behavior change>
PR contents:
- Doc edits limited to the surface that actually changed.
- Scenario updates limited to scenarios the change actually breaks.
- Hard cap: 2 new scenarios per run. Prefer updating an existing scenario over adding a new one. If you would exceed the cap, leave a TODO comment in the PR body listing the deferred scenarios.
Hard constraints
- Do not edit
docs/purely for tone or grammar — out of scope. - Do not touch
AGENTS.md,CLAUDE.md, or.itx/from this skill. - If the diff is unclear, open the PR anyway with
[draft]in the title and request input from the author of the originating commit (one short PR-body line: "@ — please confirm the user-facing wording"). - Never merge your own PRs. The PR opens against
mainand waits for human review.
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 · 76 lines · 27 tokens per session scan A d1e6188aa9e8
docs-sync is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed 14d ago), licensed Apache-2.0. It adds 27 tokens to every session and 662 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
load-github-action-thread
Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.
uv-workflow
Use when a coding agent needs to run Python code, modules, one-liners, tools, tests, or standalone scripts through uv, or create and maintain PEP 723 scripts with uv init/add/remove --script. Avoid direct python/python3 shell entrypoints.
simulate-contracts
Compile the contract set in your head — simulate how the real application would run from the specs, and disprove (or confirm) it works before any source .py is written.
author-test-stubs
Author test stub files (.pyi) whose signatures express the domain, relationships, and compositions, as the first contract surface.
model-data-schema
Author the persistence schema as a binding contract from the captured external shapes and the interview — before any test stub is written.
review-test-stubs
Review the test stubs for coverage, scope, vacuous-assertion freedom, finding-grounded scope, and happy-path completeness against the interview and the modeled schema — not for code quality.