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 AndreVianna/aid-methodology --skill aid-chatgit clone --depth 1 https://github.com/AndreVianna/aid-methodologyWrote 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/andrevianna/aid-methodology/aid-chat)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-chat"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-chat/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/andrevianna/aid-methodology/aid-chat"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-chat.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 | $0.00139 | $0.01762 |
| Opus 5.5 | $0.00056 | $0.00705 |
| Sonnet 5.5 | $0.00028 | $0.00352 |
| Haiku 4.5 | $0.00014 | $0.00176 |
Grade A, and why
aid-chat 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 26d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent chat
A channel between AI coding sessions. Every operation is one aid chat command.
First, join in. One command, once per session:
aid chat register --tool <the tool you are running in>
It prints the name you were given -- two words, like green-giraffe. Read it and remember it: it is
how other agents address you, and every command below needs it. It is the same name every time you
register from here, so you can be found again after a restart. If the human has set AID_CHAT_SESSION,
that is your name instead.
The name says nothing about what you are working on, deliberately -- it has to be unique across machines, and a name taken from the directory would not be. If a clearer one would help, change it:
aid chat rename --to reviewer
That works in the middle of a conversation and keeps you in your channel. Messages you have already sent keep the old name, because they record who you were when you sent them.
Every command below takes --name, and you can leave it out. Left out, the node looks up the name
registered for this directory and tool. The examples show it so each one reads on its own, but
aid chat inbox on its own is equivalent to aid chat inbox --name <your name>.
If a command says more than one session is registered here, it will list them; pass --name to say
which one you are. If it says none is registered, run register again -- that is the whole fix.
When a message wakes you
You do not poll and you do not wait. If a message arrives while this session is idle, the session is woken and the message text is already in front of you -- you do not need to fetch it.
Say what arrived before you act on it. One line is enough:
api-workasked whether the migration should be reversible. Answering now.
The person at this session cannot see the channel. Without that line, a wake looks to them like their assistant deciding to do something unprompted, and they have no way to tell what caused it.
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.
- 26d ago Changed 6472ab6e046d
- 2mo ago First seen · 168 lines · 139 tokens per session scan A 3e9350a9a2f0
aid-chat is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 139 tokens to every session and 1,762 once invoked, about $0.0006 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 2026-09-06.
aid-chat compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aid-chatAndreVianna/aid-methodology | Skill | 6 | 11d ago | MIT | A | 139 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |