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/dkoly/skillid/claude-mdgit clone --depth 1 https://github.com/dkoly/skillidWhat 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 | $0.00566 | $0.00566 |
| Opus 5 | $0.00283 | $0.00283 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
skillid 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 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.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillid — Project Instructions for Claude Code
This is a Claude Code plugin that enforces org-level agent guardrails via policy-driven hooks and skills.
Architecture
policy.yaml— single source of truth. All rules are data, not code.hooks/— Python scripts that fire on Claude Code tool calls (PreToolUse / PostToolUse).runtime.py— shared helper: reads stdin events, emits JSON decisions, handles audit.registry.py— auto-discovers connector resolvers fromhooks/connectors/.pre_tool_use.py— generic enforcer for all connectors. One script, not per-tool.post_tool_read.py— redacts tool output forread_redactedresources.connectors/<name>.py— per-connector resolver. Extracts resource keys from tool inputs, maps tool names to operations.
skills/— Claude Code skills (SKILL.md files). Guidance the model sees in context..claude-plugin/plugin.json— plugin metadata.
Key design principles
- Fail-closed: unknown tools in a known connector → denied. Unresolvable reads/writes → denied, except explicit list/enumeration operations.
- Single generic hook:
pre_tool_use.pyhandles all connectors via the registry. Don't create per-tool hook scripts. - Policy as data: all rules live in
policy.yaml. Hook logic is generic. - Skills are concise: under 600 tokens each. Model gets awareness; hooks do enforcement.
- Adding a connector = add YAML section + one resolver file in
hooks/connectors/. Seeskills/adding-connectors/SKILL.md.
Resource modes
| Mode | Reads | Writes | Model sees content? |
|---|---|---|---|
read_write |
✅ | ✅ | Yes |
read_only |
✅ | ❌ denied | Yes |
read_redacted |
✅ (redacted) | ❌ denied | PostToolUse attempts replacement; not true isolation |
blocked |
❌ denied | ❌ denied | No |
Testing
pip install -r requirements.txt
python3 -m pytest tests/ -v
Integration tests run hooks as subprocesses with temp policy files — no mocking of stdin/stdout needed.
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 · 46 lines · 566 tokens per session scan A 2db6bb6ed191
skillid CLAUDE.md is an instructions file published in the GitHub repository dkoly/skillid (0 stars, last pushed 2mo ago), licensed MIT. It adds 566 tokens to every session, about $0.0028 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
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.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.