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 phuonghx/aim-cli --skill verify-changesgit clone --depth 1 https://github.com/phuonghx/aim-cliWrote 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/phuonghx/aim-cli/verify-changes)<a href="https://agentmods.dev/skills/phuonghx/aim-cli/verify-changes"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/verify-changes/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/phuonghx/aim-cli/verify-changes"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/verify-changes.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 | $0.00092 | $0.00962 |
| Opus 5 | $0.00046 | $0.00481 |
| Sonnet 5 | $0.00018 | $0.00192 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
verify-changes scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:3000/api/orders | jq . How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Changes
Existing code and working code are not the same thing. Reading a function tells you what it looks like; running it tells you what it does. This skill is about closing that gap with evidence you can point to.
The distinction that matters
Inspecting: "the function is right there, so it should work" -> not verified
Assuming: "the types line up, so it must be correct" -> not verified
Executing: "I ran it; here is the output; it works, because X" -> verified
Only the third kind counts. Everything else is a hypothesis.
How to verify
1. Pin down what changed
- Which files did you touch?
- What behavior should now be different?
- What was the original requirement or bug?
2. Match the change to a method
| Kind of change | How you prove it works |
|---|---|
| Bug fix | Re-run the exact scenario that failed; confirm it no longer does |
| New feature | Drive the feature end to end; confirm the output matches intent |
| Refactor | Run the existing tests; confirm nothing regressed |
| API change | Call the endpoint; confirm the response shape and status |
| UI change | Render the component; confirm what appears on screen |
| Config change | Load the app with it; confirm the new values take effect |
| Build / infra | Run the build or pipeline; confirm it completes |
3. Actually run it
# JavaScript / TypeScript project
npm run build # does it compile?
npm test # do the tests pass?
npm run dev # does it boot?
# Smoke-test a single module
node -e "require('./src/parser'); console.log('module loads')"
# Hit an HTTP endpoint
curl -s http://localhost:3000/api/orders | jq .
# Exercise a CLI
python -m mytool --check
4. Write down the evidence
## Verification
Changed
- src/orders/total.ts — corrected rounding on multi-currency carts
Ran
- npm run build, npm test, manual curl against /api/orders
Result
- Build: compiled clean
- Tests: 58 passed, 0 failed
- Runtime: server boots; /api/orders returns the expected JSON
- Edge case: empty cart returns 0, not NaN
Still open
- Load behavior under concurrency not yet measured
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 · 125 lines · 92 tokens per session scan A a1647557fe8a
verify-changes is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 962 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
backpropagation
Trace runtime bugs back to spec gaps — identify missing acceptance criteria, update specs, generate regression tests, and detect patterns.
triage-bug
Use when triaging a bug from session evidence (evidence-capture JSONL, replay JSONL, telemetry, repo-audit) instead of from a live user description, and producing a TDD fix plan plus a docs/bugs/{slug}.md triage artifact.
audit-then-fanout-fix
When a class of bug keeps slipping through tests, run a coverage-matrix audit first, then fan out fix agents per gap — don't whack-a-mole individual failures.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
ai-discover
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.