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 instructions/proluct/skanna/claude-mdgit clone --depth 1 https://github.com/proluct/skannaWrote 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/instructions/proluct/skanna/claude-md)<a href="https://agentmods.dev/instructions/proluct/skanna/claude-md"><img src="https://agentmods.dev/badge/instructions/proluct/skanna/claude-md.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 | $0.00193 | $0.00193 |
| Opus 5 | $0.00097 | $0.00097 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
skanna CLAUDE.md 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 4d 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.
What it actually says
skanna repo conventions
Public repository. Everything committed here ships to the world.
- No em-dash or en-dash characters anywhere; use a comma, colon, period, or hyphen. No emojis.
- The skill lives in
skills/skanna/. One rule family per file underreferences/rules/; every rule needs a Benign look-alikes section and an inert fixture inexamples/. - Fixtures are inert by construction:
example.invaliddomains, fake keys, nothing that resolves or runs. - Never commit personal data, absolute local paths, tokens, or anything machine-specific.
- The scanner itself must stay dependency-free: no API keys, no external tools beyond git for cloning. Read and reason is the design.
- Verify changes by scanning
examples/benign/(must come back SAFE) andexamples/suspicious/(must come back DANGEROUS) with the updated skill.
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.
- 4d ago First seen · 11 lines · 193 tokens per session scan A b0a3d3708751
skanna CLAUDE.md is an instructions file published in the GitHub repository proluct/skanna (6 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session, about $0.0010 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 instructions, from other repositories
trustcard AGENTS.md
Instructions for davidnichols-ops/trustcard, covering trustcard — repo knowledge for agents, what this is, commands, architecture map (lib/) and entry points.
wa AGENTS.md
AGENTS.md instructions for yolo-labz/wa, covering agents.md — reviewer rules for yolo-labz/wa, daemon-reliability gates, real-liveness — claude.md r26, watchdog / auto-heal — claude.md r27 and diagnosable before fix — claude.md r28.
wa CLAUDE.md
Claude Code instructions for yolo-labz/wa, covering claude.md, project status, reliability principles (load-bearing), mission and decisions already locked in.
wafergraph-mcp CLAUDE.md
Claude Code instructions for jasonpalmer1/wafergraph-mcp, covering file map, architecture, deploy, usage telemetry and correctness/availability hardening (2026-08-08).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.