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 skills/gadievron/raptor/github-evidence-kitnpx skills add gadievron/raptor --skill github-evidence-kitgit clone --depth 1 https://github.com/gadievron/raptorWrote 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/gadievron/raptor/github-evidence-kit)<a href="https://agentmods.dev/skills/gadievron/raptor/github-evidence-kit"><img src="https://agentmods.dev/badge/skills/gadievron/raptor/github-evidence-kit.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 | $0.00062 | $0.02518 |
| Opus 5 | $0.00031 | $0.01259 |
| Sonnet 5 | $0.00012 | $0.00504 |
| Haiku 4.5 | $0.00006 | $0.00252 |
Grade A, and why
github-evidence-kit 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 yesterday.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
42 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.
- conftest.py 4.1 KB runs code
- pytest.ini 108 B
- requirements.txt 483 B
- scripts/ingest_bq_events.py 4.1 KB runs code
- scripts/init_investigation.py 3.0 KB runs code
- self_improvement_prompt.md 1.3 KB
- src/__init__.py 3.7 KB runs code
- src/clients/__init__.py 280 B runs code
- src/clients/gharchive.py 5.9 KB runs code
- src/clients/git.py 7.3 KB runs code
- src/clients/github.py 4.3 KB runs code
- src/clients/wayback.py 1.9 KB runs code
- src/collectors/__init__.py 338 B runs code
- src/collectors/api.py 9.6 KB runs code
- src/collectors/archive.py 10 KB runs code
- src/collectors/local.py 3.3 KB runs code
- src/collectors/wayback.py 2.7 KB runs code
- src/helpers.py 3.8 KB runs code
- src/parsers.py 17 KB runs code
- src/schema/__init__.py 1.9 KB runs code
- src/schema/common.py 3.4 KB runs code
- src/schema/events.py 3.4 KB runs code
- src/schema/observations.py 5.5 KB runs code
- src/store.py 9.4 KB runs code
- src/verifiers/__init__.py 141 B runs code
- src/verifiers/consistency.py 16 KB runs code
- tests/__init__.py 36 B runs code
- tests/conftest.py 11 KB runs code
- tests/fixtures/gharchive_amazon_q_timeline_evidence.json 18 KB
- tests/fixtures/gharchive_july13_2025.json 39 KB
- tests/fixtures/github_api_commits.json 1.9 KB
- tests/fixtures/github_api_pr7710.json 788 B
- tests/test_clients.py 7.6 KB runs code
- tests/test_collectors_local.py 2.0 KB runs code
- tests/test_deleted_claim_failclosed.py 3.2 KB runs code
- tests/test_gharchive_recovery.py 7.0 KB runs code
- tests/test_helpers.py 7.4 KB runs code
- tests/test_ingest_bq_events.py 6.5 KB runs code
- tests/test_integration.py 18 KB runs code
- tests/test_parsers.py 20 KB runs code
- tests/test_root_conftest_bridge.py 6.3 KB runs code
- tests/test_store.py 12 KB runs code
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.
- yesterday First seen · 362 lines · 62 tokens per session scan A b4e9a20bbf19
github-evidence-kit is a skill published in the GitHub repository gadievron/raptor (3,709 stars, last pushed 3d ago), with no licence file. It adds 62 tokens to every session and 2,518 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 skills, from other repositories
github-secret-hunting
Find leaked API keys, tokens, and credentials in public GitHub repositories.
Incident Response & Digital Forensics
IR playbook execution, evidence collection, forensic timeline analysis, memory forensics, and post-incident reporting following NIST SP 800-61 and SANS PICERL methodology.
source-verification
Walks through structured verification of sources, claims, images, video, and documents across five verification modes — visual media, documents, anonymous sources, expert credentials, and social media content — using the SIFT framework, forensic metadata inspection, deepfake indicators, C2PA Content Credentials, and…
verify
Test a behaviour claim as an investigator and report whether the evidence confirms or refutes it — CONFIRMED / REFUTED / INCONCLUSIVE with bash-captured evidence. Use when asked to verify a claim, prove a fix works, or check that a PR does what it says.
qa-test
Run an automated QA flow against a CLI or a locally-served app and report step-level pass/fail with evidence. Use when asked to QA-test a feature, exercise a flow end-to-end, or smoke-test what a PR changed.
fable-thinking
Reasoning protocol distilled from Claude Fable 5.1. Makes any model reason like Fable — evidence-grounded claims, multi-hypothesis diagnosis, concrete simulation, adversarial self-review, calibrated outcome-first delivery. Its never-skipped Floor check catches simple-looking trick questions models answer confidently…