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/phuonghx/aim-cli/code-review-checklistnpx skills add phuonghx/aim-cli --skill code-review-checklistgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00067 | $0.00751 |
| Opus 5 | $0.00034 | $0.00376 |
| Sonnet 5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
code-review-checklist 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Checklist
A reviewer's running checklist. Walk the categories, flag what's missing, and tag findings by severity.
Fast Pass
Does it work?
- Behaves as intended
- Edge and boundary cases covered
- Failures are caught and handled
- No glaring logic errors
Is it safe?
- All external input validated and cleaned
- No injection paths (SQL, NoSQL, command, etc.)
- No XSS or CSRF openings
- No credentials or secrets baked into the source
- AI-specific: guarded against prompt injection where relevant
- AI-specific: model output cleaned before it reaches a sensitive sink
Is it fast enough?
- No N+1 query pattern
- No redundant loops or repeated work
- Caching applied where it pays off
- Effect on bundle/artifact size weighed
Is it clean?
- Names communicate intent
- No copy-pasted logic
- Solid design boundaries respected
- Abstraction pitched at the right level
Is it tested?
- New paths have unit coverage
- Edge cases exercised
- Tests are readable and stable
Is it documented?
- Tricky logic explained
- Public interfaces described
- README refreshed if behavior changed
Reviewing AI / LLM Code
Logic and fabrication risk
- Reasoning path: does the logic hold up when traced end to end?
- Failure states: are empty results, timeouts, and partial responses handled?
- Outside world: are assumptions about the filesystem or network actually safe?
Prompt construction
// Weak — raw user text, no structure or guardrails
const reply = await model.complete(userText);
// Strong — explicit role, cleaned input, enforced output shape
const reply = await model.complete({
role: "You parse invoices into JSON and nothing else.",
input: clean(userText),
schema: InvoiceSchema,
});
Smells Worth Flagging
// Unexplained literal
if (state === 2) { /* ... */ }
// Named instead
if (state === OrderState.SHIPPED) { /* ... */ }
// Arrow-shaped nesting
if (a) { if (b) { if (c) { /* ... */ } } }
// Flattened with guards
if (!a) return;
if (!b) return;
if (!c) return;
// ...real work
// One enormous function -> several focused ones
// Escape-hatch typing -> precise types
const payload: any = fetchIt(); // avoid
const payload: Invoice = fetchIt(); // prefer
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.
- yesterday First seen · 100 lines · 67 tokens per session scan A fc2de6bb3262
code-review-checklist is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 751 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).