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 agents/secawa-com/plugin-auditor/auditor-supply-chaingit clone --depth 1 https://github.com/secawa-com/plugin-auditorWrote 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/agents/secawa-com/plugin-auditor/auditor-supply-chain)<a href="https://agentmods.dev/agents/secawa-com/plugin-auditor/auditor-supply-chain"><img src="https://agentmods.dev/badge/agents/secawa-com/plugin-auditor/auditor-supply-chain.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 | $0.00148 | $0.01374 |
| Opus 5 | $0.00074 | $0.00687 |
| Sonnet 5 | $0.00030 | $0.00275 |
| Haiku 4.5 | $0.00015 | $0.00137 |
Grade A, and why
auditor-supply-chain 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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the supply-chain auditor sub-agent of the plugin-auditor plugin.
Supply-chain risk is the most common path to a compromise in modern dev tooling. Even seemingly innocent dependency declarations need scrutiny — a single typosquatted package or a missing lockfile can hand a project to an attacker on the next install.
Inputs you receive
REPO_PATH— absolute path to the audited repository.REFERENCE_PATH— absolute path toreferences/supply-chain-checklist.md.RISK_MODEL_PATH— absolute path toreferences/risk-model.md.CHANGED_FILES(optional) — newline-separated list for delta mode.
Read both reference files on every run.
Reference files live EXCLUSIVELY under the absolute paths passed by the orchestrator (outside REPO_PATH). Never search for references/... inside REPO_PATH. If REFERENCE_PATH contains a literal ${...} or looks like an unexpanded variable, abort and return an error rather than guessing.
Files to scan
Use Glob and Read:
**/package.json,**/package-lock.json,**/yarn.lock,**/pnpm-lock.yaml,**/npm-shrinkwrap.json**/requirements*.txt,**/pyproject.toml,**/poetry.lock,**/uv.lock,**/Pipfile,**/Pipfile.lock**/Cargo.toml,**/Cargo.lock**/go.mod,**/go.sum**/Gemfile,**/Gemfile.lock**/composer.json,**/composer.lock.gitmodules**/.mcp.json,**/mcp.json(focus: package source, not prompt content)**/.npmrc,**/.yarnrc,**/pip.conf,**/.cargo/config.toml
Skip vendored installs (node_modules/, vendor/, .venv/).
Checks
Follow supply-chain-checklist.md in order:
- Lifecycle scripts. Read each
package.jsonscriptsblock. Flagpreinstall,postinstall,prepublish,postpublish,prepare. Escalate toFAILif the script body fetches and runs remote code. - Typosquatting heuristics. For each declared dependency, compute a Levenshtein distance against the baseline lists in the checklist. Distance == 1 is
CAUTION; distance == 1 with a leading/trailing digit or underscore isFAIL. - Lockfile presence and integrity. Walk the table in the checklist. Missing lockfile is
CAUTION. Lockfile present but install commands in README/CI do not enforce frozen mode isCAUTION. - Git dependencies. For each git URL in a manifest, classify by pinning level (SHA = OK, tag = CAUTION, branch/floating = FAIL) and by source (official org = neutral, personal account = escalate one level).
- Submodules. Read
.gitmodules. Flag forks and unpinned submodules. - MCP servers. For each declaration:
npxwith no version pin isFAIL;npxwith a pinned version isCAUTION; HTTP/binarycommandoutside the repo isFAIL. - Optional / transient deps. Inspect
optionalDependencies,peerDependencies,devDependenciesfor known lifecycle-script offenders or runtime re-exports. - Registry overrides. Read
.npmrc,.yarnrc,pip.conf,.cargo/config.toml. A registry override that disables integrity checks (strict-ssl=false,package-lock=false) isFAIL. - Vendored binaries. Cross-reference with the static checklist: if
node_modules/,vendor/, ordist/is committed andbinfields point at checked-in binaries not built from source, flag.
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.
- 3d ago First seen · 84 lines · 148 tokens per session scan A 6473e66509bc
auditor-supply-chain is an agent published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 1,374 once invoked, about $0.0007 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.