Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MountainUnicorn/addnpx agentmods add skills/mountainunicorn/add/agents-mdWrote 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/skills/mountainunicorn/add/agents-md)<a href="https://agentmods.dev/skills/mountainunicorn/add/agents-md"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mountainunicorn/add/agents-md"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.02440 |
| Opus 5.5 | $0.00013 | $0.00976 |
| Sonnet 5.5 | $0.00006 | $0.00488 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
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 2mo 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADD AGENTS.md Skill v{{VERSION}}
Generate a portable AGENTS.md at project root from the project's .add/ state. AGENTS.md is the cross-tool open standard for project-level agent instructions — any agent (Claude Code, Cursor, Codex CLI, Windsurf, Amp, Devin, Copilot) will read it on session start. Publishing one lets mixed-toolchain teams respect the same invariants without installing ADD.
This skill is the only way to regenerate AGENTS.md. A PostToolUse hook marks the file stale when source inputs change — the human triggers the actual regeneration.
Invocation
/add:agents-md # default: --write
/add:agents-md --check # drift detection, CI-friendly (exit 1 on drift)
/add:agents-md --merge # prepend ADD block to an existing hand-curated AGENTS.md
/add:agents-md --import # one-time absorption (same as --merge; explicit intent)
/add:agents-md --dry-run # preview without writing (combines with any mode)
Pre-Flight Checks
-
Read
.add/config.json- Load
project.name,project.description - Load
maturity.level(poc | alpha | beta | ga) - Load
architecture.languages— determines whether the TDD Discipline section applies - Load
environments.*.autoPromote— determines the autonomy ceiling summary
- Load
-
Read
docs/prd.mdif present- The H1 + first paragraph become the project identity section
- If absent, fall back to
project.descriptionfrom config
-
Read
.add/handoff.mdif present- Extract the currently-active spec reference (first
specs/*.mdmatch in the file) - If absent, pick the most recently mutated
specs/*.mdby mtime
- Extract the currently-active spec reference (first
-
Check
.add/agents-md.stale- If present, announce the stale state and the source files that changed since the last regen
- This marker is removed automatically after a successful
--write
-
Detect existing
AGENTS.md- No file → default
--writecreates it fresh - File with ADD marker block →
--writereplaces managed content, preserves user-authored content outside the markers - File without ADD marker →
--writeaborts with guidance to use--mergeor--import - Frontmatter (YAML / TOML /
+++) at top is preserved verbatim
- No file → default
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.
- 2mo ago First seen · 231 lines · 32 tokens per session scan A e21b81c20e65
agents-md is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 2,440 once invoked, about $0.0001 per session on Opus 5.5. 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.
agents-md compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agents-mdMountainUnicorn/add | Skill | 11 | 13d ago | MIT | A | 32 | Claude Code |
| swarmrmzi/portable-dev-system | Skill | 24 | 3mo ago | none | A | 24 | Claude Code |
| finishrmzi/portable-dev-system | Skill | 24 | 3mo ago | none | A | 26 | Claude Code |
| grillrmzi/portable-dev-system | Skill | 24 | 3mo ago | none | A | 28 | Claude Code |
| teamrmzi/portable-dev-system | Skill | 24 | 3mo ago | none | A | 23 | Claude Code |
| ticketrmzi/portable-dev-system | Skill | 24 | 3mo ago | none | A | 45 | Claude Code |
| triagermzi/portable-dev-system | Skill | 24 | 3mo ago | none | A | 24 | Claude Code |