Borrowing it
Nothing to install: this file belongs to prashantsinghmangat/TraceBug-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/prashantsinghmangat/TraceBug-ai/main/.claude/skills/gates/SKILL.mdgit clone --depth 1 https://github.com/prashantsinghmangat/TraceBug-aiWrote 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/prashantsinghmangat/tracebug-ai/gates)<a href="https://agentmods.dev/skills/prashantsinghmangat/tracebug-ai/gates"><img src="https://agentmods.dev/badge/skills/prashantsinghmangat/tracebug-ai/gates/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/prashantsinghmangat/tracebug-ai/gates"><img src="https://agentmods.dev/badge/skills/prashantsinghmangat/tracebug-ai/gates.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 | $0.00025 | $0.00707 |
| Opus 5.5 | $0.00010 | $0.00283 |
| Sonnet 5.5 | $0.00005 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
gates 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 4d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Always go through node scripts/check.mjs. Never run the npm gates one at a time, and never paste
their full output — a passing ext:lint alone is 751 lines that have been byte-identical for phases.
- Code only:
node scripts/check.mjs(typecheck, lint, test, build) - Extension files touched:
node scripts/check.mjs --full(adds build:ext, ext:lint, check:versions) - Firefox is NOT a gate.
npm run ext:firefoxisweb-ext run: it opens Firefox and stays running until the browser is closed, so it returns no verdict and cannot be wrapped. check.mjs refuses it. At the end of a phase that touched the extension, runnpm run ext:firefoxdirectly and LOOK at the result — then report what you saw, or say you could not check it. - One gate:
node scripts/check.mjs test --verboseprints full output even when a gate passes. Rarely what you want.
Report the summary lines it prints, verbatim. They already carry the counts
(658 passed, 40 files · errors 0, warnings 69 · all surfaces on 1.10.1).
When a gate fails
- check.mjs prints the last 40 lines of that gate's output. Read those first.
- One failing test:
npx vitest run <file> --reporter=dot. Don't re-run the suite to see one failure. ext:lintreporting NEW: baseline is N means this change added a web-ext warning. Fix it. Only updatescripts/check-baseline.jsonwhen the user approves a new baseline.ext:lintsaying below the N baseline is good news: a warning went away. Lower the baseline in the same step, or it stops catching the next regression.check:versionsfailing means a release surface drifted frompackage.json. It names the file. It checks ten surfaces, so fix them all rather than the one you were thinking about.- A gate failing with "could not read the Validation Summary" means web-ext's output format moved, not that the extension is clean. Look at the output before believing anything.
e2e
Not part of check.mjs — they launch real browsers and take minutes. Run only the suite related to the
change: node e2e/<name>.e2e.mjs.
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.
- 4d ago First seen · 46 lines · 25 tokens per session scan A 541946a20190
gates is a skill published in the GitHub repository prashantsinghmangat/TraceBug-ai (4 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 707 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.