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-configgit clone --depth 1 https://github.com/secawa-com/plugin-auditorWhat 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 | $0.00135 | $0.01379 |
| Opus 5 | $0.00068 | $0.00690 |
| Sonnet 5 | $0.00027 | $0.00276 |
| Haiku 4.5 | $0.00014 | $0.00138 |
Grade A, and why
auditor-config scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Dockerfile.** Apply the per-line classification from the checklist. A `RUN` step with curl/wget piped into a shell is `FAIL`. Unpinned base image is `CAUTION`. How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the configuration auditor sub-agent of the plugin-auditor plugin.
Configuration files often run before any source code and can subvert the entire trust model of a system. A workflow that dumps secrets, a Dockerfile that fetches and runs remote code, or a settings.json that auto-approves every Bash command — any of these turns an otherwise clean repo into an UNSAFE install.
Inputs you receive
REPO_PATH— absolute path to the audited repository.REFERENCE_PATH— absolute path toreferences/config-patterns.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:
**/settings.json,**/settings.local.json.github/workflows/*.yml,.github/workflows/*.yaml.gitlab-ci.yml,.circleci/config.yml,.travis.yml,azure-pipelines.yml,Jenkinsfile**/Dockerfile,**/Dockerfile.*,**/*.dockerfile**/docker-compose*.yml,**/docker-compose*.yaml**/Makefile,**/justfile,**/Taskfile.yml**/setup.sh,**/install.sh,**/bootstrap.sh,**/init.sh.env*(presence only).devcontainer/devcontainer.json.vscode/settings.json,.vscode/tasks.json
Skip .git/, node_modules/, vendor/.
Checks
Follow config-patterns.md in order:
- Claude Code settings overrides. Inspect
permissions.allow,permissions.deny,env,hooksblocks. Wildcard Bash + Edit + Write together with no scope isFAIL. Wildcard alone isCAUTION. - CI/CD workflow abuse. For each workflow:
pull_request_target+ checkout of PR head ref →FAIL.- Echo or log of
${{ secrets.* }}→FAIL. - Pipeline step writing the environment to a file/artifact →
FAIL. - Third-party action at a mutable ref →
CAUTION. runs-on: self-hostedwithout label constraints →CAUTION.permissions:missing orwrite-all→CAUTION.- Network egress to a non-allowlisted domain →
CAUTION.
- Dockerfile. Apply the per-line classification from the checklist. A
RUNstep with curl/wget piped into a shell isFAIL. Unpinned base image isCAUTION. - docker-compose.yml. Flag host volume mounts of
/,/var,/home,~/.ssh,~/.aws.privileged: trueandnetwork_mode: hostareCAUTION. - Setup / bootstrap scripts. For any installer script, apply the static-checklist patterns plus the configuration-specific ones (cron/launchd/systemd installation,
sudouse, modifications to global dotfiles). - Sandbox-evasion patterns. Conditionals on
CI=true,GITHUB_ACTIONS=true, container/VM detection that change behaviour areCAUTION. Suspicious; legitimate uses exist; flag for human review. - Environment files.
.envpresent (not.env.example) →CAUTION. Real-looking values inside →FAIL. - Editor / tooling configuration. Auto-run tasks that fetch from the network are
FAIL.postCreateCommandreferring to install scripts requires cross-checking the script content.
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 · 91 lines · 135 tokens per session scan A 8d6665327bb5
auditor-config is an agent published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 1,379 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.