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/willackerly/rebar/rebar-auditnpx skills add willackerly/rebar --skill rebar-auditgit clone --depth 1 https://github.com/willackerly/rebarWhat 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 | $0.00471 |
| Opus 5 | $0.00030 | $0.00235 |
| Sonnet 5 | $0.00012 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
rebar-audit 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 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.
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.
What it actually says
rebar-audit — run and READ the status surfaces
Steps
rebar audit— REBAR CLI compliance audit; sectioned score out of 10 (rebar itself expects 9–10/10).scripts/ci-check.sh— the full enforcement-script suite; the exit code is the verdict, the output names each failing check.scripts/steward.sh --summary— one-liner: contract counts by computed lifecycle, open discoveries, enforcement passing. A fullscripts/steward.shrun writesSTEWARD_REPORT.md+architecture/.state/steward-report.json.
The two vocabularies (do not conflate)
Computed lifecycle (draft/active/testing/impl-present) is derived by
the steward from file presence, while declared maturity
(stub/draft/in-progress/active/verified) is an honest human/agent
declaration of how real the artifact is. Canonical definitions:
rebar:convention (§Lifecycle Status Definitions, §Declared Maturity) —
resolve with scripts/rebar-doc.sh rebar:convention --cat (or rebar doc
if the CLI is installed).
- Computed shows up in steward output: the
--summarycounts, theSTEWARD_REPORT.mdtable, the.stateJSON.impl-presentmeans implementation files exist — it does NOT mean proven. - Declared shows up as
Status:lines in artifact headers (architecture/CONTRACT-*.md) and is weighted into the compliance badge byscripts/check-compliance.sh. Only this vocabulary may sayverified(active + passing tests/scenarios proving it).
Report what the surfaces actually printed, not what you expected.
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 · 38 lines · 60 tokens per session scan A 11096cb98a26
rebar-audit is a skill published in the GitHub repository willackerly/rebar (5 stars, last pushed 21d ago), licensed Apache-2.0. It adds 60 tokens to every session and 471 once invoked, about $0.0003 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
adk-unit-design
Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…
bigquery-ai-ml
Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).
code-review-skill
Reviews code with feedback tailored to the developer's profile in session state.
adk-verify-snippets
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…
adk-setup
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…
Apify Automation
Automate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.