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 skills add alexei-led/cc-thingz --skill reviewing-instructionsgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/reviewing-instructions)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/reviewing-instructions"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/reviewing-instructions/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/alexei-led/cc-thingz/reviewing-instructions"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/reviewing-instructions.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 | $0.00080 | $0.01575 |
| Opus 5 | $0.00040 | $0.00788 |
| Sonnet 5 | $0.00016 | $0.00315 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
reviewing-instructions 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction Review
Review AI-facing instruction files for routing precision, behavioral signal, output contracts, failure handling, grounding, and score stability. Do not score ordinary docs or source code.
Read first
references/scoring-rubric.mdfor gates, 0-10 bands, caps, confidence, and output schema.references/model-resolution.mdfor model alias mapping and fallback rules.references/skill-architecture.mdonly when reviewingSKILL.md,AGENT.md,body.md, or agent-facing references loaded by them.references/calibration.mdonly when a score is borderline or confidence is low.references/models/<family>.mdonly after model family resolution.
Accepted inputs
The user may pass:
- file path, directory path, or plugin name
- omitted scope, meaning discover likely instruction files
--model <name>to override model family or variant- requests such as lint, audit, review, score, compare, or rerank
A name without a path separator expands to matching src/skills/<name> or
src/agents/<name>.md. If it matches src/.agentbundler/packages/<name>.json, use the package JSON
only as routing evidence for agent-facing markdown or prompt files when the user
explicitly asks for instruction scoring. Route plugin manifest review to
evolving-config.
Scope boundaries
Review only markdown or prompt files that guide an AI agent or coding assistant. Include support files only when an entrypoint tells the agent to read them or when they live under that skill or agent folder. For plugins, score only agent-facing markdown or prompt files; never score package JSON.
Do not review:
- application source code, tests, or generated artifacts
- ordinary README, changelog, product, or design docs unless agent-facing
- package manifests such as
src/.agentbundler/packages/*.json; useevolving-config - harness config quality; use evolving-config
- code quality; use reviewing-code
If a candidate is ambiguous, put it in Candidates Not Reviewed with the reason.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .agentbundler/targets/claude.json 2.3 KB
- references/calibration.md 2.4 KB
- references/model-resolution.md 1.9 KB
- references/models/claude.md 1.3 KB
- references/models/generic.md 807 B
- references/models/openai.md 820 B
- references/scoring-rubric.md 11 KB
- references/skill-architecture.md 3.0 KB
- scripts/lint-instructions.py 29 KB runs code
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.
- 12d ago First seen · 182 lines · 80 tokens per session scan A b45ecaf3f815
reviewing-instructions is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,575 once invoked, about $0.0004 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.