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 skills/harshanandak/forge/agents-md-editnpx skills add harshanandak/forge --skill agents-md-editgit clone --depth 1 https://github.com/harshanandak/forgeWrote 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/harshanandak/forge/agents-md-edit)<a href="https://agentmods.dev/skills/harshanandak/forge/agents-md-edit"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/agents-md-edit.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 | $0.00073 | $0.00805 |
| Opus 5 | $0.00036 | $0.00402 |
| Sonnet 5 | $0.00015 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
agents-md-edit 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agents-md-edit
AGENTS.md has two audiences in one file. Put your sentence in the wrong half
and it either ships to every Forge user or disappears at the next regenerate.
The two blocks
<!-- FORGE:START -->…<!-- FORGE:END -->— the product contract. It is rendered by Forge and it ships to users. It must read as if written for someone who has never seen this repository: noscripts/, nolefthook.yml, no.agents/skills, no machine paths, no maintainer trivia. Never hand-edit it to record something you learned while building Forge.<!-- USER:START -->…<!-- USER:END -->— ours. The maintainer contract: what we never compromise on, the glossary, the hit-every-surface checklist, the ways to hurt yourself, the dev runbook.
The renderer preserves the USER block across regeneration. smartMergeAgentsMd
extracts it by regex and re-emits it, so its content survives forge setup
regardless of where you put it — but it is re-emitted above the FORGE block,
so do not depend on its position. [verified 2026-08-13 — lib/smart-merge.js]
Before you write a line
- Which audience? If the sentence names a repo-local path, a script, a
hook file, or a test, it belongs in the USER block or in
.forge/contributor-skills/. Product-facing text names commands, not files. - What is the evidence? Every rule carries a provenance tag —
[Forge #N ×n]for a mined correction,[verified DATE]for something read out of running code,[imported]for a borrowed default with no local incident. Untagged rules get deleted at the next re-mine. [§5.9-8] - Does it beat the default? Delete any sentence a competent agent would have followed anyway. Prompt the behaviour you want; naming the banned behaviour drags it into context.
- Is it short? If a rule needs paragraphs to defend, it is the wrong rule.
Committing it
AGENTS.md is protected state. Read protected-commit before you stage it —
as of 2026-08-13 the gate has no writer that can authorize an AGENTS.md
commit, including a USER-block-only edit. Never reach for --no-verify.
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.
- 5d ago First seen · 65 lines · 73 tokens per session scan A 3ed17ab84819
agents-md-edit is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 805 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…