Borrowing it
Nothing to install: this file belongs to Wynelson94/longhand. 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/Wynelson94/longhand/main/CLAUDE.mdgit clone --depth 1 https://github.com/Wynelson94/longhandWrote 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/instructions/wynelson94/longhand/claude-md)<a href="https://agentmods.dev/instructions/wynelson94/longhand/claude-md"><img src="https://agentmods.dev/badge/instructions/wynelson94/longhand/claude-md.svg" alt="Measured on agentmods" 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 | $0.01006 | $0.01006 |
| Opus 5 | $0.00503 | $0.00503 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
longhand CLAUDE.md 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 7d 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.
Longhand MCP Tools — Efficient Usage Guide
Quick Decision Tree
When a user asks about past work:
-
"Do you remember when..." → Use
recallFIRST. It handles fuzzy time, project matching, and retrieval in one call, returning a narrative built from conversation segments and session timelines — plus high-precision problem→fix episodes when the work left clean evidence. -
"Find X in session Y" → Use
searchwithsession_id+context_events+ a natural-language query. Returns matches WITH surrounding conversation. Do NOT paginateget_session_timelinemanually. -
"What happened in session X?" → Use
get_session_timelinewithsummary_only: truefirst to scan, thensearch(withsession_id+context_events) to drill into specifics. Usetail: Nfor how the session ended or the latest events. -
"What file did we edit?" → Use
get_file_historyorreplay_file. -
"What did we commit?" → Use
find_commits— pass aqueryfor cross-session search, or asession_idwith no query for one session's chronological git story. -
"Where did we leave off on X?" → Use
recall_project_statuswith the project name. Returns recent commits, unresolved issues, last session outcome, and conversation context in one call. Git-aware when git data exists, degrades gracefully without it.
Anti-Patterns (AVOID)
- Never paginate
get_session_timelinein a loop looking for something. Usesearchwithsession_id+context_eventsinstead. - Never use
searchwithoutsession_idwhen you know which session to look in. Unscoped search returns noise from all sessions. - Never skip
recallfor "do you remember" questions. It was built for exactly this use case. - Don't call the retired names —
search_in_context,get_latest_events,get_project_timeline,get_session_commits,get_episode,match_projectleft the tool listing at 1.0. They still answer forever (with a migration preamble) so older docs never hard-fail, but the surviving tools take the same parameters directly.
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.
- 7d ago First seen · 55 lines · 1,006 tokens per session scan A 65256628bbfd
longhand CLAUDE.md is an instructions file published in the GitHub repository Wynelson94/longhand (13 stars, last pushed 25d ago), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.