Borrowing it
Nothing to install: this file belongs to lsampaioweb/ai-instructions. 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/lsampaioweb/ai-instructions/main/.cursor/skills/review-code-against-instructions/SKILL.mdgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/lsampaioweb/ai-instructions/review-code-against-instructions)<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/review-code-against-instructions"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/review-code-against-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/lsampaioweb/ai-instructions/review-code-against-instructions"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/review-code-against-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00084 | $0.01151 |
| Opus 5.5 | $0.00034 | $0.00460 |
| Sonnet 5.5 | $0.00017 | $0.00230 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
review-code-against-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 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Instruction Audit
Arguments
- Optional target path, module, file, or glob.
- Omit the filter to audit the full workspace.
1. Define the Scope
- Load all instruction files applicable to the target scope from both:
- the workspace directory
.github/instructions/ - the configured user-level directory
~/.agents/instructions/
- the workspace directory
- Check each instruction file's
applyTopattern against the target files. - Treat both locations as active instruction sources. Do not ignore an applicable user-level instruction because it is outside the workspace.
- If applicable instructions conflict, report the conflict and identify both sources. Stop rather than choosing a winner silently.
- Resolve the target scope from the user-provided arguments when present. If missing, audit the full workspace.
- Enumerate all code files in scope, sorted by path ascending.
- Read each code file and check it against all applicable instructions.
- If scope exceeds available context, process files in path order until context is exhausted, then set Verdict to CONTINUE and record the next unprocessed path.
Project decision records
- Load project ADRs or equivalent decision records from the target workspace,
typically under
docs/adr/, when they exist. - Treat an ADR as an approved, project-specific exception only when all of the
following are true:
- its status is
Acceptedor equivalent; - it explicitly names the behavior, endpoint, component, or rule being decided;
- the observed code is within the ADR's stated scope;
- the ADR does not merely describe the current implementation.
- its status is
- An explicit accepted ADR may override a reusable instruction only for the narrowly described decision. Do not generalize the exception to unrelated code or rules.
- Continue validating every non-exempt instruction and every compensating control described by the ADR.
- Cite the ADR when suppressing a finding. If the ADR is ambiguous, obsolete, superseded, or broader than the observed decision, report the uncertainty and stop instead of silently accepting the exception.
- Do not treat README text, comments, deployment assumptions, or undocumented conventions as equivalent to an accepted ADR.
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 Changed · +33 lines · +20 tokens per session 00373fe77df0
- 2mo ago First seen · 93 lines · 64 tokens per session scan A 012c0f5731b0
review-code-against-instructions is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 84 tokens to every session and 1,151 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 2026-08-31.
review-code-against-instructions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-code-against-instructionslsampaioweb/ai-instructions | Skill | 1 | 5d ago | MIT | A | 84 | Cursor |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 5d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |