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 Veridise/audithub-skills --skill orcagit clone --depth 1 https://github.com/Veridise/audithub-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/veridise/audithub-skills/orca)<a href="https://agentmods.dev/skills/veridise/audithub-skills/orca"><img src="https://agentmods.dev/badge/skills/veridise/audithub-skills/orca.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 5.1 | $0.00088 | $0.00893 |
| Opus 5 | $0.00044 | $0.00447 |
| Sonnet 5 | $0.00018 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
audithub-orca 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 7d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
40 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.
- audithub-orca-call-metrics-analyzer/agents/openai.yaml 210 B
- audithub-orca-call-metrics-analyzer/SKILL.md 2.2 KB
- audithub-orca-campaign-orchestrator/agents/openai.yaml 209 B
- audithub-orca-campaign-orchestrator/SKILL.md 8.4 KB
- audithub-orca-counterexample-analyzer/agents/openai.yaml 216 B
- audithub-orca-counterexample-analyzer/SKILL.md 2.9 KB
- audithub-orca-final-reporter/agents/openai.yaml 191 B
- audithub-orca-final-reporter/SKILL.md 2.6 KB
- audithub-orca-hint-writer/agents/openai.yaml 188 B
- audithub-orca-hint-writer/SKILL.md 2.3 KB
- audithub-orca-live-state-setup/agents/openai.yaml 207 B
- audithub-orca-live-state-setup/SKILL.md 5.7 KB
- audithub-orca-local-deployment-builder/agents/openai.yaml 228 B
- audithub-orca-local-deployment-builder/SKILL.md 2.8 KB
- audithub-orca-property-discoverer/agents/openai.yaml 211 B
- audithub-orca-property-discoverer/SKILL.md 1.9 KB
- audithub-orca-setup-tuner/agents/openai.yaml 192 B
- audithub-orca-setup-tuner/SKILL.md 3.5 KB
- audithub-orca-smoke-run-debugger/agents/openai.yaml 207 B
- audithub-orca-smoke-run-debugger/SKILL.md 4.3 KB
- audithub-orca-target-selector/agents/openai.yaml 210 B
- audithub-orca-target-selector/SKILL.md 1.9 KB
- audithub-orca-v-spec-writer/agents/openai.yaml 207 B
- audithub-orca-v-spec-writer/SKILL.md 5.3 KB
- README.md 3.8 KB
- references/call-metrics-and-tuning.md 2.9 KB
- references/campaign-state-and-autonomy.md 5.5 KB
- references/hints-library 33 B
- references/live-state-setup.md 3.4 KB
- references/local-deployment.md 2.3 KB
- references/orca-deployment-script-builder.md 872 B
- references/orca-docs 24 B
- references/orca-fuzzing-campaign-planner.md 1.3 KB
- references/orca-hint-writer.md 703 B
- references/orca-result-analyzer.md 1.1 KB
- references/orca-v-spec-writer.md 1015 B
- references/smoke-tests.md 3.5 KB
- references/specs-and-counterexamples.md 6.0 KB
- references/target-selection.md 2.3 KB
- references/vspec-library 28 B
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.
- 7d ago First seen · 55 lines · 88 tokens per session scan A 31fe48f79a02
audithub-orca is a skill published in the GitHub repository Veridise/audithub-skills (23 stars, last pushed 19d ago), with no licence file. It adds 88 tokens to every session and 893 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
performing-api-fuzzing-with-restler
Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…
performing-fuzzing-with-aflplusplus
Perform coverage-guided fuzzing of compiled binaries using AFL++ (American Fuzzy Lop Plus Plus) to discover memory corruption, crashes, and security vulnerabilities. The tester instruments target binaries with afl-cc/afl-clang-fast, manages input corpora with afl-cmin and afl-tmin, runs parallel fuzzing campaigns with…
Form Validation Breaker
Exhaustive testing of form validation logic including boundary values, injection payloads, encoding edge cases, and client-server validation bypass techniques.
API Fuzzing
API endpoint fuzzing for discovering unexpected behaviors, crashes, and security vulnerabilities through malformed requests, boundary values, and protocol violations.
cairo-testing
Cairo smart-contract testing with snforge. Trigger on "write tests", "add unit tests", "fuzz test", "integration test", "test this contract", "regression test". Guides test strategy, cheatcode usage, and coverage.
att&ck
Exhaustively test each MITRE ATT&CK technique.