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 AndreVianna/aid-methodology --skill aid-reviewgit clone --depth 1 https://github.com/AndreVianna/aid-methodologyWrote 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/andrevianna/aid-methodology/aid-review)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-review"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-review/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/andrevianna/aid-methodology/aid-review"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-review.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 | $0.00133 | $0.02849 |
| Opus 5 | $0.00067 | $0.01425 |
| Sonnet 5 | $0.00027 | $0.00570 |
| Haiku 4.5 | $0.00013 | $0.00285 |
Grade A, and why
aid-review 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 8d 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.
Review (run now, produce findings)
/aid-review performs a review now and returns grade + findings +
recommendations. It is the adversarial sibling of /aid-ask: both are single-shot,
grounded, cited, and never plan-and-halt -- review evaluates an existing artifact against
criteria, where /aid-ask answers a free-form question.
- Not a numbered pipeline phase. It runs on demand; it does not enter the
Discover->Execute flow and never routes to
/aid-execute. - Read-only except: the findings ledger (a
.tempartifact) and, only after your approval, a publish to the reviewed target (a PR/ticket comment, doc notes). It never edits the reviewed code/design itself and never fixes -- fixing is/aid-fix's job.
State machine: INTAKE -> REVIEW -> VERIFY (loop) -> PRESENT-FINDINGS [human] ->
PUBLISH (on approval) -> DONE. Print the state-entry line on entry to each state
([State: NAME] -- {one-line purpose}), the convention every AID skill uses.
State: INTAKE
Purpose: resolve the target + criteria, pick the path, allocate the work folder.
Step 1 -- require a target
If the argument is empty, ask exactly one bootstrapping question and wait:
What do you want to review? Point me at a file/dir, a PR, a ticket id, a
work-NNN, "my changes", or describe the target.
Step 2 -- pick the path (fast vs guided)
Fast path -- the prompt carries an explicit, resolvable target whose review method is unambiguous. Record the target, method, and tentative delivery; go straight to REVIEW.
| Signal | Method | Tentative delivery |
|---|---|---|
PR link / #123 |
diff review | PR comment(s) via gh |
ticket id (PROJ-45) |
assess ticket content | ticket comment via /aid-update-ticket |
| file / dir path | static review vs KB + coding-standards | findings report |
| "my changes" / working tree / staged | working-diff review | findings report |
| commit SHA / range / branch | diff review | findings report or PR comment |
work-NNN or an AID artifact (REQUIREMENTS/SPEC/PLAN/DETAIL) |
review vs its acceptance criteria + KB | findings in the work folder |
a KB doc (.aid/knowledge/*.md) |
review vs the KB-authoring rubric | findings report |
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.
- 8d ago First seen · 220 lines · 133 tokens per session scan A c4a993fe87f3
aid-review is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 2,849 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…