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/open-agent-tools/postcard/claude-mdgit clone --depth 1 https://github.com/Open-Agent-Tools/PostcardWrote 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/open-agent-tools/postcard/claude-md)<a href="https://agentmods.dev/instructions/open-agent-tools/postcard/claude-md"><img src="https://agentmods.dev/badge/instructions/open-agent-tools/postcard/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 | $0.01105 | $0.01105 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
Postcard 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 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — notes for future agents editing this repo
Context you'll need that isn't obvious from the code.
Version bumps touch four files
Every release bumps these together; CI checks nothing about this, so a mismatched set is easy to ship accidentally:
.claude-plugin/plugin.json.claude-plugin/marketplace.jsonpyproject.tomlsrc/oat_postcard/__init__.py(__version__)
Also add a CHANGELOG.md entry and git tag -a vX.Y.Z.
The plugin runs under macOS system Python 3.9
Hook scripts call python3, which on macOS is /usr/bin/python3 (3.9
via Xcode CLT). This means:
- Every src module starts with
from __future__ import annotationsso PEP 604 (X | None) doesn't blow up at import time. requires-python = ">=3.9"inpyproject.toml.- Adding a type annotation that evaluates at runtime (e.g. a default
argument using
X | Y) is a silent plugin-breaker on macOS system Python. Prefer annotations that are purely annotations.
Hook scripts must be self-contained
Claude Code's behavior on firing hooks:
CLAUDE_PLUGIN_ROOTis sometimes set, but not reliably early enough. Hooks derive their own path via$(dirname "$0")/...bin/auto-registers on PATH after the plugin is loaded, but hooks must still refer to the shim via the self-relative path — don't assume PATH has been set up yet.set -uwill abort on any unset env var. Hooks useset -eo pipefail(no-u) and${var:-}guards around optional payload fields.
Session identity has four fallbacks
session.current_session_id() tries, in order:
$CLAUDE_SESSION_IDenv var (set by Claude Code; not always propagated to tool Bash invocations).$OAT_POSTCARD_SESSIONenv var (manual override for tests).- PID-chain walk:
os.getpid() → ppid → ppid → ...until an ancestor PID matches a live directory entry. - TTY:
tty:$(tty)for standalone terminal use.
If you're adding a new entry point, be mindful that option 3 depends
on the directory entry's PID being stable. Always pass --pid "$PPID"
from hook scripts (which is Claude Code's PID), not os.getppid()
from inside the shim (which is transient bash).
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.
- 3d ago First seen · 111 lines · 1,105 tokens per session scan A 9be8f4379b88
Postcard CLAUDE.md is an instructions file published in the GitHub repository Open-Agent-Tools/Postcard (2 stars, last pushed 24d ago), licensed MIT. It adds 1,105 tokens to every session, about $0.0055 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.
Other instructions, from other repositories
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.
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.