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 epicsagas/epic-harness --skill vuln-scangit clone --depth 1 https://github.com/epicsagas/epic-harnessWrote 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/epicsagas/epic-harness/vuln-scan)<a href="https://agentmods.dev/skills/epicsagas/epic-harness/vuln-scan"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/vuln-scan/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/epicsagas/epic-harness/vuln-scan"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/vuln-scan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.01803 |
| Opus 5 | $0.00023 | $0.00901 |
| Sonnet 5 | $0.00009 | $0.00361 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
vuln-scan 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vuln Scan — Systematic Vulnerability Scanner
Iron Law
Code you haven't traced from input to sink has vulnerabilities you haven't found. A grep hit is a lead, not a finding.
Process
Step 0: Load Engagement Context
Check for .harness/engagement.md. If present, load scope constraints — only scan in-scope paths and respect exclusions.
Check for THREAT_MODEL.md from a previous /threat-model run. If present, use its threat scenarios as scan targets. If absent, run full-surface scan.
Step 1: Map Entry Points to Trust Boundaries
Enumerate every place untrusted data enters the system, by reading the code:
- External → app: HTTP handlers/routers, GraphQL resolvers, webhooks, file uploads, form fields, query params, headers
- Process boundary: CLI args, environment variables, IPC, deserialization of stored data (cache, DB rows written earlier, config files)
- Client-supplied state: cookies, JWT claims, API keys, referer/origin
For each entry point, note: what validation exists (yes/no/partial), and where the data flows next. This list is the scan's backbone — a scan that cannot name its entry points has not started.
Step 2: Trace Data Flow to Sinks
From each entry point, follow the data by reading code until it reaches a dangerous operation, or dies (validated, parameterized, dropped). Dangerous sink classes:
| Sink class | Examples (non-exhaustive) |
|---|---|
| Command/code execution | shell invocation, eval-family, template engines with code modes, deserialization to live objects |
| Query construction | string-built SQL, raw-query escapes in any ORM (Knex raw, Prisma $queryRaw, SQLAlchemy text(), Sequelize literal, Django extra/raw, Rails where("...") with interpolation) |
| Filesystem | path joins with user input, upload destinations, archive extraction (zip-slip), file reads driven by request params |
| Web output | template rendering with non-auto-escaping engines, innerHTML-family, redirect targets, header values (CRLF) |
| Auth decisions | IDOR — object lookups keyed only on user-supplied ids without ownership checks; role checks done client-side or per-endpoint instead of per-object |
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 Changed · -20 lines · +11 tokens per session 23a213abeb0d
- 11d ago First seen · 166 lines · 35 tokens per session scan A 3b8475b7447f
vuln-scan is a skill published in the GitHub repository epicsagas/epic-harness (18 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,803 once invoked, about $0.0002 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
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
toxic-senior-reviewer
Code review in the voice of a toxic senior developer — dry sarcasm without profanity, no fluff, no empty praise. Use this skill whenever the user asks for a code review, says "how can I improve this", "what do you think of this code", "take a look at this", "rate this solution", "critique this", "do a code review"…
execute-plan
Execute an approved plan step-by-step with a checkpoint after each. Triggers on execute the plan, run the plan, do the steps, implement the plan.