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-mercato/skills/agents-mdgit clone --depth 1 https://github.com/open-mercato/skillsWrote 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-mercato/skills/agents-md)<a href="https://agentmods.dev/instructions/open-mercato/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/open-mercato/skills/agents-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 5.1 | $0.03723 | $0.03723 |
| Opus 5 | $0.01861 | $0.01861 |
| Sonnet 5 | $0.00745 | $0.00745 |
| Haiku 4.5 | $0.00372 | $0.00372 |
Grade A, and why
skills 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 today.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
This repository is the source of the Open Mercato Skills collection: thirty-seven agent skills (skills/<name>/SKILL.md) that run a full PR pipeline — plan, implement, review, QA gate, merge — installable into any repo via skills.sh. The deliverables here are markdown skill documents plus a small amount of shell/Node tooling; there is no application code.
Task routing
| When the task involves… | Read first | Key rules |
|---|---|---|
Editing or adding a skill (skills/<name>/SKILL.md) |
DECISIONS.md, scripts/lint.sh, the Cross-skill contract section below, the skill's own references/ dir if present |
Frontmatter name must equal the directory name and description must be present (≤500 chars — lint-enforced; aim for ≤350). Content must stay product-agnostic: no Open Mercato product references, no hard-coded base branch or package manager (the lint gate greps for these). All tracker state management goes through named tracker operations, never direct gh commands (only references/trackers/ may contain them). Config values (baseBranch, paths, labels, validation commands) always come from .ai/agentic.config.json, never hard-coded. New om-auto-* skills MUST implement the Cross-skill contract. |
| Cross-skill contracts (tracker operations, config schema, Progress format) | skills/om-setup-agent-pipeline/SKILL.md, skills/om-setup-agent-pipeline/references/trackers/TEMPLATE.md, BACKWARD_COMPATIBILITY.md |
Multiple skills parse each other's outputs (execution-plan Progress sections, test-env.json, tracker descriptors). Changing a shared format requires updating every consumer in the same PR. |
Installer / tooling scripts (scripts/*.sh, scripts/*.mjs) |
package.json, the script itself, .github/workflows/ |
Keep scripts POSIX-portable where they run in CI (ubuntu) and locally (macOS). scripts/lint.sh is the CI gate — changes to it change what every PR must pass. |
CI workflows (.github/workflows/*.yml) |
scripts/lint.sh, scripts/audit-skills.sh |
lint.yml runs the frontmatter + product-agnosticism gate on every PR. skills-audit.yml is informational (skills.sh third-party audit surfacing). |
| Process / pipeline configuration | .ai/agentic.config.json, SDLC.md, .ai/trackers/github.md |
Config and SDLC.md describe the same process — change them together. |
| README, DECISIONS.md, LICENSE | DECISIONS.md |
These MAY reference the upstream Open Mercato project (the agnosticism gate is scoped to skills/** only). Read DECISIONS.md before proposing structural changes — most "obvious" restructurings were already considered and decided. |
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.
- today Changed · +51 tokens per session 95d5bd170600
- 5d ago First seen · 105 lines · 3,672 tokens per session scan A 23e4567797d3
skills AGENTS.md is an instructions file published in the GitHub repository open-mercato/skills (141 stars, last pushed today), licensed MIT. It adds 3,723 tokens to every session, about $0.0186 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.
Other instructions, from other repositories
attractor-guided-engineering-template AGENTS.md
AGENTS.md instructions for entropy-cloud/attractor-guided-engineering-template, covering agents.md, project intent, dual-audience repo, in-tree tool and task routing.
a-i--skills 03-development-workflow.instructions.md
Instructions for organvm-iv-taxis/a-i--skills, covering development workflow instructions, no repo-wide build system, common development commands, after adding/modifying skills and validation before committing.
context-to-action-skills AGENTS.md
Instructions for tmusser/context-to-action-skills, covering agents, repo model, safety rules, output rules and validation commands.
piratebao copilot-instructions.md
Instructions for d4551/piratebao: PirateBao kraken active by default. Respond like pirate captain packing dumpling cargo: dense, exact, no wasted wrap.
Physical-AI-Humanoid-Robotics-Book GEMINI.md
Gemini CLI instructions for DevExplorerr/Physical-AI-Humanoid-Robotics-Book, covering gemini cli rules, task context, core guarantees (product promise), development guidelines and 1. authoritative source mandate.
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.