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/mistakeknot/interdoc/skill-and-featuresgit clone --depth 1 https://github.com/mistakeknot/interdocWhat 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 | $0.00000 | $0.00533 |
| Opus 5 | $0.00000 | $0.00267 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
skill-and-features 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill & Features
Cross-AI documentation for interdoc. Works with Claude Code, Codex CLI, and other AI coding tools.
Why AGENTS.md? Claude Code reads both AGENTS.md and CLAUDE.md, but AGENTS.md is the cross-AI standard that also works with Codex CLI and other AI coding tools.
The Skill
| Skill | Trigger | Use Case |
|---|---|---|
interdoc |
Natural language (hooks disabled by default) | Generate/update AGENTS.md documentation |
Discovery: In Claude Code, ask "List all available Skills" to see interdoc, or run /interdoc.
Advisory hook (optional): Run ./hooks/git/install-post-commit.sh to enable a non-blocking reminder after commits.
Optional modes: Use phrases like "change-set update", "doc coverage", or "doc lint" to trigger specialized behaviors.
Note: This is a Claude Code plugin skill, invoked via natural language (e.g., "generate documentation for this project"). It is NOT a slash command.
Key Features
- Parallel subagents: Spawns agents per directory for fast analysis
- Incremental updates: Appends new content, preserves existing documentation
- CLAUDE.md harmonization: Migrates docs from CLAUDE.md → AGENTS.md
- Unified diff previews: Shows actual diffs before applying
- Dry run + cached apply: Preview changes and apply last preview without re-analysis
- Structural auto-fix: Deterministic rename/deletion/link fixes without LLM tokens (
/interdoc fix) - JSON schema output: Subagents return structured JSON with sentinel markers
- Git-aware: Uses commit messages and diffs for update context
- Scalability guardrails: Concurrency limits, batch processing for large repos
- Claude subagent option: Specialized subagent for high-quality AGENTS.md content
Interwatch Integration
interdoc is a generator target for interwatch's drift-detection framework. When interwatch detects that AGENTS.md has drifted (files renamed/deleted/created, commit threshold exceeded), it dispatches to interdoc:interdoc-engine for regeneration. interdoc does not compute drift scores — interwatch owns detection, interdoc owns generation. The scripts/interdoc-generator.sh marker file signals generator availability to interwatch's discovery system.
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 · 41 lines · 0 tokens per session scan A 13e1a2307349
skill-and-features is an agent published in the GitHub repository mistakeknot/interdoc (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 533 tokens. 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.
.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.