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 skills add jmagly/aiwg --skill doc-consolidategit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/skills/jmagly/aiwg/doc-consolidate)<a href="https://agentmods.dev/skills/jmagly/aiwg/doc-consolidate"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/doc-consolidate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jmagly/aiwg/doc-consolidate"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/doc-consolidate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00023 | $0.03461 |
| Opus 5 | $0.00012 | $0.01731 |
| Sonnet 5 | $0.00005 | $0.00692 |
| Haiku 4.5 | $0.00002 | $0.00346 |
Grade A, and why
doc-consolidate 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Consolidate
You are the Doc Consolidate Orchestrator — crawling a repository for documentation scattered across directories and building a consolidated reference index in .aiwg/docs/ for planning, ops, semantic memory, and release-associated documentation.
Core Philosophy
Repos accumulate docs everywhere: README files in every package, deployment guides in ops/, release notes at root, API docs in docs/api/, troubleshooting buried in wiki-style folders. This skill answers: "what docs exist, where are they, and what are they for?"
No file duplication. Copying docs creates parallel drift. Instead, build a reference manifest and lightweight stubs that point to originals.
Natural Language Triggers
Users may say:
- "consolidate docs"
- "doc consolidate"
- "find all docs"
- "catalog docs"
- "inventory docs"
- "doc inventory"
- "where are all the docs"
- "what docs do we have"
- "gather documentation"
- "index all documentation"
- "consolidate documentation for planning"
Parameters
--dry-run (optional)
Preview all discovered docs and their classifications without writing any files. Produces the same report as a live run but with no mutations.
--scope <path> (optional)
Limit discovery to a subtree. Useful for large monorepos.
/doc-consolidate --scope docs/
/doc-consolidate --scope packages/auth/
--incremental (optional)
Only process files changed since the last successful run. Reads timestamp from .aiwg/reports/doc-consolidate-last-run.json. Falls back to full scan if no prior run exists.
--prefix <dir> (optional)
Target a different project directory instead of the current working directory.
Categories
| Category | What belongs here | Path heuristics |
|---|---|---|
release |
Changelogs, release notes, version announcements | CHANGELOG*, docs/releases/*, *release-note* |
user |
User guides, tutorials, quickstarts, how-tos | README*, docs/getting-started*, docs/quickstart*, docs/guide* |
api |
API references, SDK docs, integration guides | docs/api/*, *-reference.md, *-api.md, *cli-reference* |
deployment |
Deploy guides, runbooks, infra docs | docs/deploy*, ops/*, *runbook*, *infrastructure* |
planning |
Roadmaps, RFCs, proposals, ADRs | *roadmap*, *rfc*, *proposal*, ADR-*, docs/planning/* |
communications |
Announcements, blog posts, marketing | *announcement*, *blog*, *press*, *marketing* |
help |
Troubleshooting, FAQ, support docs | *troubleshoot*, FAQ*, *support*, *error-reference* |
development |
Contributing guides, dev setup, coding standards | CONTRIBUTING*, docs/development/*, docs/contributing*, *coding-standard* |
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.
- 6d ago Changed 2dcef5238574
- 9d ago First seen · 411 lines · 23 tokens per session scan A c11c16e0e49f
doc-consolidate is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 3,461 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.