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 commands/yeaight7/agent-powerups/bug-checkgit clone --depth 1 https://github.com/yeaight7/agent-powerupsWhat 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 | $0.00025 | $0.00355 |
| Opus 5 | $0.00013 | $0.00178 |
| Sonnet 5 | $0.00005 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
bug-check 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 3d 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.
What it actually says
/bug-check — Automated Bug Check
Mandatory automated checks precede agent review. Do not skip or reorder steps.
Usage
/bug-check [path|.]
Step 1 — Automated Tests (mandatory, cannot skip)
npm test # or: pytest, cargo test, go test ./...
npm run build # TypeScript build / type check
- Tests fail → report as highest priority; stop here until fixed
- Build fails → report type errors as highest priority; stop here until fixed
- Both pass → continue to Step 2
Step 2 — Focused Code Review
Review for patterns that automated tests do not catch:
- Execution path parity — do all code paths (sandbox, production, feature-flag variants) return the same response shape?
- Query completeness — are all fields used in the response present in the query?
- Error state cleanup — is stale state cleared when an error is returned?
- Optimistic update rollback — is UI state reverted when an API call fails?
Step 3 — Regression Tests
For every bug found and fixed, record one of:
Bug: <description>
File: <path>
Regression test: <test name and assertion>
or if a test cannot be written now:
Bug: <description>
Regression test: DEFERRED — <reason>
Do not silently skip. An explicit deferral is required.
Arguments
$ARGUMENTS:
[path|.]— optional target path
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.
- 3d ago First seen · 56 lines · 25 tokens per session scan A ee49f05c8041
bug-check is a command published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 355 once invoked, about $0.0001 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 commands, from other repositories
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
t800-bootstrap
Запускайте один раз при установке плагина или для новичка в чате.
validate-pipeline
Validate data pipeline configuration and data quality rules.
advisor
Get a second opinion from Codex (GPT-5) on your current plan, diff, or a specific question.
aidd-pr
Review a PR, resolve addressed comments, and generate /aidd-fix delegation prompts for remaining issues.