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 instructions/coctostan/pi-hashline-readmap/agents-mdgit clone --depth 1 https://github.com/coctostan/pi-hashline-readmapWrote 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/coctostan/pi-hashline-readmap/agents-md)<a href="https://agentmods.dev/instructions/coctostan/pi-hashline-readmap/agents-md"><img src="https://agentmods.dev/badge/instructions/coctostan/pi-hashline-readmap/agents-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 | $0.01176 | $0.01176 |
| Opus 5 | $0.00588 | $0.00588 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
pi-hashline-readmap AGENTS.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 5d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Developer & Agent Guide
Repo-local guide for working on pi-hashline-readmap.
What This Project Is
pi-hashline-readmap is a unified pi extension that replaces several built-in tools with enhanced versions:
read— hashlined reads, structural maps, symbol-addressable readsedit— hash-anchored edits with semantic diff summariesgrep— hashlined search resultsast_search— ast-grep wrapper with hashlined outputbashfiltering — command-aware output compression
The extension is loaded via an absolute path entry in ~/.pi/agent/settings.json's extensions array (pointing at this workspace's index.ts), so new agent sessions pick up local edits automatically. Running sessions do not hot-reload the module graph — restart any in-flight agent session to see changes take effect.
Version Control
This repo is currently operated as a normal git repo with GitHub PRs. Do not assume jj is configured here.
Standard flow:
git checkout main
git pull --ff-only origin main
git checkout -b feat/my-feature
# edit / test
git add -A
git commit -m "feat: my feature description"
git push -u origin feat/my-feature
gh pr create --base main --head feat/my-feature
After merge:
git checkout main
git pull --ff-only origin main
git branch -d feat/my-feature
Use git branch -D only after verifying the work is on origin/main.
Megapowers-managed work
When /mega on is active, do not run ad-hoc branch/commit/push commands outside the allowed workflow moments. Use megapowers tools for phase changes and TDD signals. Post-merge cleanup on local main is the main exception.
Development
Prereqs:
node --version # >= 22.19.0
npm install
Useful optional tools:
brew install ast-grep
brew install difftastic
brew install shellcheck yq scc
Validation:
npm test
npm run typecheck
Source map
index.ts— extension entry pointsrc/read.ts,src/edit.ts,src/grep.ts,src/sg.ts,src/nu.ts— core tool implementationssrc/*-output.ts,src/*-render-helpers.ts— tool result shaping / renderingsrc/readmap/— structural mapping, symbol lookup, language detection, per-language mapperssrc/rtk/— bash output routing and compression techniquesprompts/— tool prompt/schema docsscripts/— helper scripts used by readmap internalstests/— feature-focused tests and fixtures
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.
- 5d ago First seen · 140 lines · 1,176 tokens per session scan A 78382f0804b7
pi-hashline-readmap AGENTS.md is an instructions file published in the GitHub repository coctostan/pi-hashline-readmap (104 stars, last pushed 17d ago), licensed MIT. It adds 1,176 tokens to every session, about $0.0059 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
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.
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).
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.
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).