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/jmacdotorg/plerd/claude-mdgit clone --depth 1 https://github.com/jmacdotorg/plerdWhat 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 | $0.02013 | $0.02013 |
| Opus 5 | $0.01007 | $0.01007 |
| Sonnet 5 | $0.00403 | $0.00403 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
plerd CLAUDE.md scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- runs the body and title through `Markdown::Perl` (a shared converter in GitHub mode, so fenced code blocks, tables, and the rest of GFM work) then `Plerd::SmartyPants`. The converter drops `"` from its HTML-escaped cha How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Plerd is an ultralight static-blog generator written in Perl (Moose-based). It turns a directory of Markdown source files into a complete static site (per-post HTML, a recent-posts front page, a single archive page, tag pages, and Atom + JSON Feed syndication documents). It is designed to pair with Dropbox: a daemon watches the source directory and republishes on change. Distributed on CPAN as Plerd.
Source code lives in lib/ and bin/.
Commands
Dependencies: cpanm --installdeps . (deps are listed in cpanfile).
Build / install (ExtUtils::MakeMaker is the canonical maker per minil.toml):
perl Makefile.PL && make && make install
Tests (they add ../lib via FindBin, so run with -l):
prove -lv t/ # whole suite
prove -lv t/basic.t # a single test file
t/basic.t is the main end-to-end test: it calls Plerd::Init::initialize to scaffold t/testblog/, copies fixtures from t/source_model/ (filenames containing TODAY get the current date substituted), publishes, and asserts on the generated files. t/daemon.t covers plerdwatcher; t/init.t covers scaffolding.
Development workflow
This project follows test-driven development. Whenever appropriate, begin work on a new feature or bug fix by writing a test that captures the desired behavior, and run it first to confirm it fails for the expected reason. Then implement the change and confirm the test passes.
(The fail-first step only applies when the test genuinely precedes the implementation. If a change has already landed and you are adding tests retroactively, just confirm the new tests pass — don't revert working code to manufacture a failing run.)
Comments document the present, never the diff. Don't write comments that narrate a change ("used to do X, now does Y"; "previously gated on…"; "no longer…"). If a comment exists only to record that the code changed, drop it; otherwise restate it as a present-tense reason the current code is the way it is. Watch for history smuggled into single words like "still", "now", or "anymore".
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.
- 2d ago First seen · 82 lines · 2,013 tokens per session scan A f51f851db889
plerd CLAUDE.md is an instructions file published in the GitHub repository jmacdotorg/plerd (117 stars, last pushed 1mo ago), licensed MIT. It adds 2,013 tokens to every session, about $0.0101 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.