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 skills add harshanandak/forge --skill forge-intakegit 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/forge-intake)<a href="https://agentmods.dev/skills/harshanandak/forge/forge-intake"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/forge-intake/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/harshanandak/forge/forge-intake"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/forge-intake.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 | $0.00034 | $0.00703 |
| Opus 5.5 | $0.00014 | $0.00281 |
| Sonnet 5.5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
forge-intake 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-intake
This prevents building on a definition the repository contradicts, or waiting on the user for a fact the agent can check.
Map
Create an intent issue with forge issue create if none exists, then read it and linked context. Keep its map on that issue: Destination, Decisions so far, Not yet specified, Out of scope. Track each decision's prerequisites and status. Assign stable ids D1, D2, and so on when discovered; never renumber or reuse them across rounds or resumes.
Facts before decisions
Facts are the agent's job: look them up in code, tools or primary sources, or dispatch a subagent. Never ask the user for a fact you can investigate. A pending investigation blocks only its dependent decisions; continue with the others.
Before dispatching any subagent, run forge route get <role> --text for its role and use the line it prints to select the dispatch.
Before each dispatch, run forge issue call <intent> --role <role> with that role; on LIMIT_REACHED stop and report. Retry REVISION_CONFLICT. Pass returned timeboxMinutes and stopBy. Tell the subagent to stop and report the checkpoint when timeboxMinutes expire, never later than stopBy. These are intake's dispatch rules.
Prototype when execution is the missing fact
A question only running code can answer gets a prototype. Name the question first. Spend at most one session and 300 lines on a prototype/<name> branch or in a scratch folder, with no tests or polish. It ends with the verdict, evidence (output, timing or screenshot) and branch pointer as a comment on the intent issue; for a scratch folder, name its source branch and folder. A validated snippet may be inlined in the slice issue. A prototype never merges; port its decision into a slice.
Rounds
- Find every open decision whose prerequisites are settled. Ask all of them in this round; defer decisions that depend on an unanswered question or pending fact.
- Number each by its stable id, give a short title and recommendation with the reason, and word the question so "yes" accepts the recommended answer. For example:
D1: Scope: Shall we deliver the command first? Recommended: yes, to prove the smallest useful path. - In an attended run, wait for answers. A bare "yes" accepts all recommendations in the current round; a reply naming ids applies only to those decisions. Keep unanswered decisions open. Silence is not an answer.
- Record answers under their existing ids, recompute prerequisites and repeat. If an answer changes, reopen only affected decisions and work; keep their ids.
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.
- 2d ago First seen · 39 lines · 34 tokens per session scan A 0d3245672443
forge-intake is a skill published in the GitHub repository harshanandak/forge (0 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 703 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 2026-10-28.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…