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 SidCorp-co/forge --skill forge-message-shapegit clone --depth 1 https://github.com/SidCorp-co/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/sidcorp-co/forge/forge-message-shape)<a href="https://agentmods.dev/skills/sidcorp-co/forge/forge-message-shape"><img src="https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-message-shape/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/sidcorp-co/forge/forge-message-shape"><img src="https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-message-shape.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 | $0.00120 | $0.04023 |
| Opus 5.5 | $0.00048 | $0.01609 |
| Sonnet 5.5 | $0.00024 | $0.00805 |
| Haiku 4.5 | $0.00012 | $0.00402 |
Grade A, and why
forge-message-shape 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 11d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The shape of a message to a person
Forge screens every message an agent writes for a person to read, and refuses the ones that do not fit. This document is that contract. It is served live over the Forge MCP prompt channel, so the copy you are reading is the current one — nothing syncs to disk, and there is no second version to go stale.
If a write of yours was refused, the refusal already told you the rule, the shape and an example. This says why the rule is there and what else is in the set.
What decides the rules: who reads it, and what it asks of them
Two questions, asked of every message, and neither of them is about where the message renders. A comment on an issue and a line in a chat room are judged by who reads them and what they claim, not by the transport that carries them.
The intent — what the reader owes after reading:
ask— the reader owes an answer. The message is a question put to somebody who can settle it.report— the reader owes nothing. The message tells them something.
The audience — what the reader holds:
role(the role holder) — somebody with a role on the project. They can open the tracker and check any claim you make, and they are the person who decides.public(no role) — somebody with no role. They cannot check a claim, cannot open an issue you name, and cannot act on a detail about our internals.
Two audiences and three intents make five cells — the pairs are sparse, not a filled grid — and a cell is the only thing that holds rules:
| cell | what it is |
|---|---|
role:ask |
a question put to somebody who can answer it |
role:report |
a comment on an issue, read by the person who decides |
role:chat |
the assistant's reply to somebody holding a role, in a Forge UI room |
public:ask |
reserved — see the bottom of this page |
public:report |
a reply to somebody who cannot open the tracker to check it |
role:product:report |
the lead of a record, where no human member of the project reads as technical |
role:technical:report |
the same lead, where one of them does |
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.
- 11d ago Changed · +31 lines 7788324758ac
- 13d ago Changed · +8 lines 2aad6e9a4a4f
- 14d ago Changed · +2 lines 9ff31ad01dce
- 15d ago Changed · +89 lines c9c8ffbfaab5
- 16d ago First seen · 172 lines · 120 tokens per session scan A a9ddb430f28e
forge-message-shape is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 4,023 once invoked, about $0.0005 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 2026-09-14.
Other skills, from other repositories
ai-seo
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
ad-creative
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
ai-agent-job-marketplace
The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.
adaptive-anti-bot-web-scraping
Adaptive web scraping framework with anti-bot bypass and spider crawling.
agent-freelance-bounty-marketplace
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.