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 skills/adamyodinsky/interactive-docs-skill/interactive-docsnpx skills add adamyodinsky/interactive-docs-skill --skill interactive-docsgit clone --depth 1 https://github.com/adamyodinsky/interactive-docs-skillWhat 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 | $0.00058 | $0.03928 |
| Opus 5 | $0.00029 | $0.01964 |
| Sonnet 5 | $0.00012 | $0.00786 |
| Haiku 4.5 | $0.00006 | $0.00393 |
Grade C, and why
interactive-docs scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
6. **Universal project support.** Never refuse a project. Adapt analysis to whatever languages and patterns exist. How it starts
The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Documentation Generator
Analyze a codebase and produce a fully interactive, locally-runnable documentation site. The output is a React + Vite + TypeScript app with 10 views, all populated from real project analysis. Run yarn dev to browse.
Execute the phases below in strict order. Do not skip or merge phases.
Phase Gate System
Every phase is guarded by gate.sh. Before starting a phase, run the gate check. After completing a phase, mark it done. This enforces sequential execution and validates prerequisites.
# Before starting Phase N:
bash "$SKILL_DIR/scripts/gate.sh" check N "$PROJECT_ROOT" "$DOCS_DIR"
# Must output "READY" — if "BLOCKED", stop and fix the issue.
# After completing Phase N:
bash "$SKILL_DIR/scripts/gate.sh" mark N "$PROJECT_ROOT"
Never skip a gate check. Never mark a phase complete before it actually succeeds.
Phase 0 — Resolve Project Root
Determine the project to document:
- If
$ARGUMENTSis non-empty, use it as the project path. Resolve relative paths against the current working directory. - If
$ARGUMENTSis empty, use the current working directory. - Validate the path exists and is a directory. If not, tell the user and stop.
Store the resolved absolute path as PROJECT_ROOT.
Store the directory containing this SKILL.md as SKILL_DIR — all script and reference paths below are relative to it.
Mark complete: bash "$SKILL_DIR/scripts/gate.sh" mark 0 "$PROJECT_ROOT"
Phase 1 — Static Analysis
Gate check: bash "$SKILL_DIR/scripts/gate.sh" check 1 "$PROJECT_ROOT"
Run the static analysis script:
bash "$SKILL_DIR/scripts/analyze.sh" "$PROJECT_ROOT"
Capture stdout as STATIC_ANALYSIS_JSON. If the script exits non-zero, report the error to the user and stop.
Extract PROJECT_NAME from the JSON's projectName field.
This JSON contains: file tree, detected languages, frameworks, dependencies, entry points, LOC per directory, env keys, config files, schema files, and optional madge dependency graph output.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ANALYSIS.md 11 KB
- references/DIAGRAMS.md 18 KB
- references/SITE_SPEC.md 24 KB
- references/TYPES.md 14 KB
- scripts/analyze.sh 16 KB runs code
- scripts/gate.sh 3.1 KB runs code
- scripts/scaffold.sh 14 KB runs code
- scripts/validate-visual.sh 2.3 KB runs code
- scripts/validate-write.sh 2.1 KB runs code
- scripts/validate.sh 783 B runs code
- scripts/visual-tests.mjs 5.8 KB runs code
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 · 393 lines · 58 tokens per session scan C 86bd97c94c89
interactive-docs is a skill published in the GitHub repository adamyodinsky/interactive-docs-skill (1 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 3,928 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
brainstorm
Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration.
self-review
Convergent multi-agent review of work you just produced — code, docs, configs, skills, plans, commit text, chat answers. Use after finishing any task that wrote or changed code, before reporting done (the Stop gate arms for code files only — prose, config, data and asset changes are reviewed on demand); whenever the…
balance-check
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.
security-claude
Skill "security-claude" from rahozosman/security-claude, covering security architecture & threat modeling intelligence, how this skill is organized (progressive disclosure), 1. pick a mode, 2. core method (applies to every mode) and 3. doing a focused review.