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 rules/danielvm-git/bigpowers/validate-fixgit clone --depth 1 https://github.com/danielvm-git/bigpowersWrote 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/rules/danielvm-git/bigpowers/validate-fix)<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/validate-fix"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/validate-fix.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.01345 |
| Opus 5 | $0.00026 | $0.00673 |
| Sonnet 5 | $0.00010 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
validate-fix 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 today.
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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Fix
HARD GATE — Fix must not regress. Run full test suite and manual UAT before declaring success.
Prove the fix works. "I think it works" is not evidence. Run the suite, show the output, then harden against recurrence.
Two-commit red/green policy (e45s08) — Bug fixes follow the same two-commit discipline as
develop-tdd: first commit adds/adjusts the failing test (test(<scope>): …), second commit applies the fix (fix(<scope>): …). Do not squash RED and GREEN before review.
Checklist
1. Re-run the originally failing test
# Run the specific test that captured the bug
<test command for the failing test>
- Previously failing test now passes
2. Run the full test suite
# Run all tests — no filtering
<full test command from CLAUDE.md>
- All tests pass (zero regressions)
3. Type check
<typecheck command>
- No type errors introduced
4. Lint
<lint command>
- No lint violations introduced
5. Harden against recurrence
For every bug fixed, add at least one prevention layer:
| Mechanism | When to use |
|---|---|
| Type guard | Input could be the wrong shape |
| Schema validation (Zod, Pydantic, etc.) | External data crossing a boundary |
| Invariant assertion | Internal state that must always hold |
| Lint rule | Pattern that's easy to repeat by mistake |
| Environment check at startup | Missing config causes silent failure |
- At least one hardening mechanism added
- Hardening mechanism is tested
5b. Generalize-fix (HARD GATE — e80s04 / GH #98)
Sweep the defect class across the codebase after local hardening — see REFERENCE-generalize-fix.md.
- Defect class documented (not just the one-line root cause)
- Grep sweep run and
match_countrecorded -
verify-generalize-sweep.shpasses on the artifact
6. Update the bug file and registry.yaml
Find the most recent specs/bugs/BUG-*.md file and append the resolution:
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.
- today First seen · 147 lines · 52 tokens per session scan A 6d881d6a8d8f
validate-fix is a cursor rule published in the GitHub repository danielvm-git/bigpowers (162 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,345 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 2026-09-03.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
app-router-patterns
Next.js 14+ App Router patterns — Server Components, Client Components, Route Handlers, Server Actions, and metadata API.
context-os
ContextOS rules for context-os.
database
Database architecture, schema design, Prisma, Drizzle ORM, indexing strategies, migrations, and N+1 query resolution.
vue
Rules for Vue (2 and 3) single-file components.
nextjs
ContextOS rules for nextjs.