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 markoblogo/abvx-agent-skills --skill bug-evidence-protocolgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/bug-evidence-protocol)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/bug-evidence-protocol"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/bug-evidence-protocol.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.01056 |
| Opus 5 | $0.00038 | $0.00528 |
| Sonnet 5 | $0.00015 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
bug-evidence-protocol 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Evidence Protocol
Record proof without replacing the workflow that produces it:
diagnoseowns reproduction, hypotheses, and root cause;test-driven-executionowns the behavior-first red/green implementation loop;- this skill captures and classifies evidence;
git-native-context-contractmay retain a recurrent lesson as acpat.
Do not scan a repository for unsolicited bugs or claim a defect from inspection alone.
Authority and approval
Invocation does not reduce authority already granted by the user. Reversible local tests and scoped code fixes may proceed when they are part of the requested task.
Stop for explicit approval before:
- production or device writes;
- destructive migrations or data mutation;
- dependency or configuration changes outside the approved scope;
- crossing security, privacy, financial, or protected-evidence boundaries;
- expanding files, behavior, or external effects materially beyond the request;
- changing production code during an audit-only or reproduce-only task.
Evidence integrity
A confirmed bug requires a valid reachable path, a defensible expected behavior, and a focused command that fails for the predicted symptom. Syntax, fixture, dependency, permission, and unrelated setup failures are INCONCLUSIVE, not REPRODUCED.
Capture the exact targeted command before and after. Preserve argv rather than a shell string. The included capture helper records:
- SHA-256 command identity;
- cwd, runtime, Git root/head/dirty state;
- hashes of selected lockfiles when present;
- time, duration, exit code, and timeout;
- bounded redacted stdout and stderr.
Never capture a full environment dump. Inspect captured artifacts before publishing them; regex redaction is a safety net, not proof that output is public-safe.
python3 <skill>/scripts/capture_command.py --label targeted-before --output before.json -- <exact command>
python3 <skill>/scripts/capture_command.py --label targeted-after --output after.json -- <exact command>
python3 <skill>/scripts/capture_command.py --label broader-tests --output broader.json -- <relevant suite>
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 105 lines · 76 tokens per session scan A 9d2d0e0f3130
bug-evidence-protocol is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,056 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
lsp-refactor
End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.