consulting-project-docs

consulting-project-docs is a skill for Claude Code, Codex from qa-vault/codelore. It costs 224 tokens per session (1,245 once invoked), scanned A, original, MIT.

A project-documentation routing instruction for coding agents. It tells the agent to find and read a project's existing documentation before planning, investigating, debugging, or changing existing functionality.

In plain words
What is it for?
Use it at the start of non-trivial work on an existing codebase, such as fixing bugs, adding features, investigating behavior, or learning how a module works.
Why use it?
It helps the agent use the project's established design and decisions instead of relying on assumptions. It also identifies when the documentation step can be skipped for trivial or entirely new work.

Skill for Claude CodeCodex

Part of the codelore plugin — 4 skills shipped together

Install

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.

agentmods
npx agentmods add skills/qa-vault/codelore/consulting-project-docs
Any agent
npx skills add qa-vault/codelore --skill consulting-project-docs
Clone the repo
git clone --depth 1 https://github.com/qa-vault/codelore

Made for: Claude Code, Codex.

Or install codelore, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for consulting-project-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/qa-vault/codelore/consulting-project-docs.svg)](https://agentmods.dev/skills/qa-vault/codelore/consulting-project-docs)
Your own site
<a href="https://agentmods.dev/skills/qa-vault/codelore/consulting-project-docs"><img src="https://agentmods.dev/badge/skills/qa-vault/codelore/consulting-project-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 224 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,245 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00224 $0.01245
Opus 5 $0.00112 $0.00622
Sonnet 5 $0.00045 $0.00249
Haiku 4.5 $0.00022 $0.00125

Measured 3d ago against content hash 08542acb0f95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consulting-project-docs 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 3d 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.

skills/consulting-project-docs/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consulting Project Docs

This skill is the front door for AI sessions that need context from a project's existing implementation documentation. Without it, agents plan and investigate without consulting the docs that contain critical context — leading to hallucinated assumptions and rework.

When to invoke

Trigger on planning/investigation/debugging verbs the user uses before asking the agent to act on existing functionality. Concrete signals:

  • "How does X work?" / "Why does Y do Z?"
  • "Plan a change to ..." / "Investigate ..." / "Fix the bug in ..."
  • "Add Feature B to the existing X module" — the X module is the part you need to load docs for, not the new feature.
  • "Onboard me onto this codebase" / "Explain this module"
  • The agent is about to call EnterPlanMode, debug a non-trivial bug, or modify a module it has not touched in this session.

Skip invocation for:

  • Trivial edits (renames, formatting, single-line bug fixes in code you've just read).
  • Pure greenfield work where no existing module is involved.
  • Tasks the user has already loaded context for in this conversation.

Workflow

1. Locate docs/INDEX.md

Look at the project root for docs/INDEX.md. In monorepos, also check one level deeper (e.g. packages/*/docs/INDEX.md, apps/*/docs/INDEX.md) and prefer the index closest to the files the user is asking about.

If no INDEX.md is found anywhere, also check whether docs/ (or doc/, documentation/) exists with .md files in it.

2. Branch on index state

State Action
INDEX.md found and recent Go to step 3 (dispatch).
No INDEX.md, but docs/ has .md files (excluding plan folders) Tell the user codelore can index these for AI sessions and offer to invoke the migrate-project-docs skill. Pause until the user accepts or declines. If declined, defer back without loading anything — do not silently grep individual docs.
No INDEX.md, no docs/ (or only plan folders) Defer back silently. There is nothing to consult; let the agent proceed with normal exploration tools.

Read the full file on GitHub · 105 lines

Changes

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.

  1. 3d ago First seen · 105 lines · 224 tokens per session scan A 08542acb0f95

Subscribe to this mod's changes

consulting-project-docs is a skill published in the GitHub repository qa-vault/codelore (2 stars, last pushed 4mo ago), licensed MIT. It adds 224 tokens to every session and 1,245 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens