Borrowing it
Nothing to install: this file belongs to BackendGameSetMatch/sourcebook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BackendGameSetMatch/sourcebook/main/.claude/skills/sourcebook-lookup/SKILL.mdgit clone --depth 1 https://github.com/BackendGameSetMatch/sourcebookWrote 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/backendgamesetmatch/sourcebook/sourcebook-lookup)<a href="https://agentmods.dev/skills/backendgamesetmatch/sourcebook/sourcebook-lookup"><img src="https://agentmods.dev/badge/skills/backendgamesetmatch/sourcebook/sourcebook-lookup/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/backendgamesetmatch/sourcebook/sourcebook-lookup"><img src="https://agentmods.dev/badge/skills/backendgamesetmatch/sourcebook/sourcebook-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00080 | $0.00545 |
| Opus 5.5 | $0.00032 | $0.00218 |
| Sonnet 5.5 | $0.00016 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
sourcebook-lookup 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 2mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Documentation Lookup
This project maintains structured AI-readable documentation in /docs/ai/.
Consult these docs BEFORE making assumptions about how systems work, what
conventions exist, what has already been decided, or which APIs we depend on.
How to search
Run the lookup script from this skill's directory:
python .claude/skills/sourcebook-lookup/scripts/lookup.py search <keywords>
python .claude/skills/sourcebook-lookup/scripts/lookup.py list [systems|processes|decisions|apis]
python .claude/skills/sourcebook-lookup/scripts/lookup.py read <path>
python .claude/skills/sourcebook-lookup/scripts/lookup.py bundle <scope>
python .claude/skills/sourcebook-lookup/scripts/lookup.py glossary [term]
python .claude/skills/sourcebook-lookup/scripts/lookup.py conventions
python .claude/skills/sourcebook-lookup/scripts/lookup.py decisions [--status active]
python .claude/skills/sourcebook-lookup/scripts/lookup.py index
python .claude/skills/sourcebook-lookup/scripts/lookup.py log
Run it with no arguments to see the full command list.
When to consult docs
- Before modifying core service or library code - search for the system or module
- Before integrating a new external API - load the bundle covering API references
- Before modifying any build, deploy, or infrastructure code - load the bundle covering it
- Before changing release workflows - read the relevant process doc
- Before suggesting an architectural approach -
list decisions - When encountering unfamiliar internal terms -
glossary <term> - When unsure about constraints -
conventions
Bundle names are project-specific. Passing an unknown scope to bundle
prints the list this project actually defines, so check there rather than
guessing a name.
Important rules
- The
decisions/directory contains Architectural Decision Records. Always check before proposing approaches. - The
conventions.mdfile contains hard constraints. Never violate these. - If docs seem stale (check
last_verifieddates), flag it rather than trusting outdated information.
What ships with it
1 file 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.
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.
- 2mo ago First seen · 55 lines · 80 tokens per session scan A a009d47f0515
sourcebook-lookup is a skill published in the GitHub repository BackendGameSetMatch/sourcebook (4 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 545 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
memo-bank-query
Load the governing spec/contract for a file or topic from a project's memo-bank (a read-only MCP docs corpus) BEFORE reading code or editing. Use this in any repo that has a .island-slices.json or a memo-bank MCP server, whenever you are about to edit a file, or are asked "what governs X", "is there a spec for Y"…
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.