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/mmartinez/postern/claude-mdgit clone --depth 1 https://github.com/mmartinez/posternWrote 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/mmartinez/postern/claude-md)<a href="https://agentmods.dev/instructions/mmartinez/postern/claude-md"><img src="https://agentmods.dev/badge/instructions/mmartinez/postern/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 | $0.02460 | $0.02460 |
| Opus 5 | $0.01230 | $0.01230 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
postern 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What postern is
A credential-brokering HTTPS forward proxy for AI agents. The agent calls outbound APIs without auth headers (or with placeholder values); postern matches the request host against YAML-declared broker rules, resolves the rule's credential reference from a pluggable credential provider (1Password Service Accounts, Bitwarden Secrets Manager, OAuth2 token minting), and injects it before forwarding. The agent never holds the real credential.
Apache-2.0 licensed.
Development environment — container-first, non-negotiable
The host needs only Docker, git, and the devcontainer CLI. No Go toolchain on the host. Every Go, lint, test, format, and vuln tool lives inside the devcontainer, version-pinned by .mise.toml.
- Start the env once:
devcontainer up --workspace-folder . - Drop into a shell:
make shell - Anything Go-related goes through
make <target>. From the host these wrapdevcontainer exec; inside the container they are direct invocations. The Makefile auto-detects which side it's on. - Bump tool versions in
.mise.toml; the devcontainer reads these pins. CI pins Go/lint/goreleaser/zig separately in each workflow's env — bump both sides when a tool changes.
If a command fails on the host with "command not found", the fix is to run it via make (or inside make shell), not to install the tool globally.
Commands
All Go work runs through make; on the host these wrap devcontainer exec.
make shell— interactive shell inside the devcontainer.make build— builddist/postern.make test— full suite with-raceand coverage.make lint— golangci-lint.make ci— lint + test + vuln + license check (the core local gate; CI adds platform, format, gitleaks, and snapshot/image jobs on top); run before pushing.make snapshot— local release build (binaries, archives, SBOMs, checksums; no publish/sign).make licenses— regenerateTHIRD_PARTY_NOTICES.mdafter any dependency change.
Project layout
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 · 148 lines · 2,460 tokens per session scan A cea31e3230ac
postern CLAUDE.md is an instructions file published in the GitHub repository mmartinez/postern (10 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,460 tokens to every session, about $0.0123 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
Cybermes AGENTS.md
Instructions for Zyrexnn/Cybermes, covering 🛡️ cybermes master operational directives (agents.md), 1. 🎯 persona & core mission, 2. ⚡ core operational principles, 3. 📁 strict target-scoped workspace & deliverables and mandatory rules for file creation.
skylos CLAUDE.md
Claude Code instructions for duriantaco/skylos, covering claude.md, what this repo is, install, use and skill for using skylos.
shipproof AGENTS.md
Instructions for kingggg5/shipproof, covering agents.md, what this repository is, non-negotiable rules, verify before declaring done and where things live.
medusa CLAUDE.md
Claude Code instructions for Pantheon-Security/medusa, covering medusa - medusa security scanning, critical: release gate — do not skip, 4. security hardening tests (must show: all pass), critical: bash sandbox and project overview.
claude-wrapper CLAUDE.md
Instructions for smartwatermelon/claude-wrapper, covering claude.md, what this is, commands, run tests and lint.
ai-harness CLAUDE.md
Instructions for samartomar/ai-harness, covering ai-harness — claude bootloader, vocabulary — two different things, read the source, not a summary of it, start here and self-hosting boundary.