agentmods.dev

skillmesh-cli AGENTS.md

Repository instructions for an AI software-delivery process in which an agent handles the engineering work and a human accepts or rejects the final pull request. It defines required records, checks, and safety rules for each run.

In plain words
What is it for?
Use it when implementing changes in the repository to create run records, plan and review files, test results, sanitized summaries, and required quality checks.
Why use it?
It makes the delivery process auditable and prevents incomplete work from reaching review without plans, tests, and a recorded verdict.

Instructions file for CodexOpenCode

4 1mo ago A scan 384 tokens original MIT
View the source file okzero/skillmesh-cli
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/okzero/skillmesh-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/okzero/skillmesh-cli

Made for: Codex, OpenCode.

Per session 384 This file is loaded in full into every session.
When invoked 384 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 $0.00384 $0.00384
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured yesterday against content hash 913788450450, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillmesh-cli 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 yesterday.

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 · 36 lines

What it actually says

Skillmesh AI Delivery Contract

This repository uses an L4 delivery workflow: an AI agent executes the full engineering cycle and a human only accepts or rejects the final pull request.

Required workflow

  1. Read the internal spec supplied for the run and record its SHA-256. Never copy private spec content into committed files or a pull request.
  2. Create a new .ai/runs/<run-id>/ directory. Run IDs are immutable; a retry uses a new ID and references the failed run in run.json.
  3. Write plan.md before editing code. Cover behavior, safety, compatibility, tests, and documentation.
  4. Implement without asking a human to edit code or make an implementation decision. If the spec is incomplete or contradictory, stop with blocked.
  5. Record material commands in commands.jsonl and checks in tests.json.
  6. Review the completed diff in review.md with verdict: PASS or FAIL.
  7. Write final.json, then run python3 scripts/l4_gate.py validate ....
  8. Put only the generated sanitized summary in the pull request. The human's only role is the final approve/reject decision.

Mandatory quality gates

  • python -m ruff check .
  • python -m mypy skillmesh
  • python -m pytest tests/ -q -p no:cacheprovider with an isolated HOME
  • python skillmesh.py --help and python skillmesh.py --version
  • No destructive test may access real Agent, config, backup, or hub paths.

Safety rules

  • Preserve runtime zero-dependency support.
  • Preserve confirmation semantics for destructive user operations.
  • Never commit secrets, personal paths, private spec text, or full transcripts.
  • Never rewrite or delete previous run evidence.
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. yesterday First seen · 36 lines · 384 tokens per session scan A 913788450450

Subscribe to this mod's changes

skillmesh-cli AGENTS.md is an instructions file published in the GitHub repository okzero/skillmesh-cli (4 stars, last pushed 1mo ago), licensed MIT. It adds 384 tokens to every session, about $0.0019 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.

Code reviewPlanningTestingai-agentsclaude-codeclicodexcursoricloud
Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

llm-safe-haven CLAUDE.md

Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens

yapcap CLAUDE.md

Claude Code instructions for TopiCsarno/yapcap, a project described as: Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.

TopiCsarno/yapcap · 3 tokens