coding-posture AGENTS.md

Repository instructions for coding-posture, a one-file collection of procedural checklists for situations where coding agents commonly make mistakes.

In plain words
What is it for?
Use them when editing the coding-posture skill or preparing a release, including synchronizing version markers and enabling the repository’s secret-scan hooks.
Why use it?
They keep the guidance focused, evidence-based, and subordinate to the user’s, project’s, and safety instructions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/alexei-led/coding-posture/agents-md
Clone the repo
git clone --depth 1 https://github.com/alexei-led/coding-posture

Made for: Codex, OpenCode.

Per session 241 This file is loaded in full into every session.
When invoked 241 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00241 $0.00241
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 2d ago against content hash 95f2919159f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-posture 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 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.

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.

AGENTS.md · 22 lines

What it actually says

Coding Posture

  • The product is one file: skills/coding-posture/SKILL.md. No engine, no selection code.
  • Modes are procedural checklists, not personas. Keep them aimed at situations models reliably get wrong.
  • A mode never overrides user/project/safety instructions.
  • Keep SKILL.md scannable: short checklists, plain mode names, no persona theatrics. Enrich modes only with practices that have evidence behind them.

Releasing

Bump the version in all four markers together, then tag vX.Y.Z:

  • package.jsonversion
  • .claude-plugin/plugin.jsonversion
  • .claude-plugin/marketplace.jsonmetadata.version, plugins[0].version, and top-level version
  • .codex-plugin/plugin.jsonversion

The Claude plugin only updates for installed users when version changes, so it must move on every release.

Local setup

Enable the bundled secret-scan hooks once per clone: git config --local core.hooksPath scripts/git-hooks (requires gitleaks).

Changes

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.

  1. 2d ago First seen · 22 lines · 241 tokens per session scan A 95f2919159f3

Subscribe to this mod's changes

coding-posture AGENTS.md is an instructions file published in the GitHub repository alexei-led/coding-posture (15 stars, last pushed 2mo ago), licensed MIT. It adds 241 tokens to every session, about $0.0012 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.