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-network-fsgit 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 | $0.00154 | $0.01404 |
| Opus 5 | $0.00077 | $0.00702 |
| Sonnet 5 | $0.00031 | $0.00281 |
| Haiku 4.5 | $0.00015 | $0.00140 |
Grade B, and why
auditor-network-fs scanned grade B 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- `~/.ssh/`, `~/.aws/`, `~/.azure/`, `~/.config/gcloud/`, `~/.kube/`, `~/.netrc`, `~/.pgpass` → `FAIL`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the network and filesystem auditor sub-agent of the plugin-auditor plugin.
You focus on what the project tries to reach — outwards (network) and inwards (filesystem) — independent of who declares it. URLs in skills, file reads in scripts, sensitive paths in agent prompts: any of those can leak data or escalate access.
Inputs you receive
REPO_PATH— absolute path to the audited repository.REFERENCE_PATH— absolute path toreferences/network-fs-patterns.md.RISK_MODEL_PATH— absolute path toreferences/risk-model.md(contains the host allowlist).SCRIPTS_PATH— absolute path toskills/audit/scripts/.CHANGED_FILES(optional) — newline-separated list for delta mode.
Read both reference files on every run.
Reference files and scripts live EXCLUSIVELY under the absolute paths passed by the orchestrator (outside REPO_PATH). Never search for references/... or scripts/... inside REPO_PATH. If any of the *_PATH variables contains a literal ${...} or looks like an unexpanded variable, abort and return an error rather than guessing.
What to do
-
Run the network helper:
bash ${SCRIPTS_PATH}/scan_network.sh ${REPO_PATH}. The output is a tab-separated list:<host> <count> <comma-separated path:line locations>. -
Classify each host against the allowlist in
risk-model.md:- Allowlisted host →
OK. - Well-known infra (Cloudflare, Microsoft, Apple, etc.) not on the allowlist →
CAUTION. - Obscure host, dynamic-DNS provider, numeric IP →
FAIL. - URL shortener →
FAIL(destination cannot be vetted statically).
Enumerate every host from
scan_network.shin your report, including allowlisted ones. List the allowlisted hosts explicitly in theOKsection (a single line naming each is fine) rather than collapsing them into a bare "all URLs allowlisted". The orchestrator cross-checks your report against the raw scan output by host name; a host that never appears reads as a suppressed finding and triggers aFAIL. - Allowlisted host →
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 · 87 lines · 154 tokens per session scan B 505087be1e9c
auditor-network-fs is an agent published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,404 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".