Borrowing it
Nothing to install: this file belongs to socket-link/ampere. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/socket-link/ampere/main/AGENTS.mdgit clone --depth 1 https://github.com/socket-link/ampereWrote 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/instructions/socket-link/ampere/agents-md)<a href="https://agentmods.dev/instructions/socket-link/ampere/agents-md"><img src="https://agentmods.dev/badge/instructions/socket-link/ampere/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/instructions/socket-link/ampere/agents-md"><img src="https://agentmods.dev/badge/instructions/socket-link/ampere/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 | $0.07603 | $0.07603 |
| Opus 5.5 | $0.03041 | $0.03041 |
| Sonnet 5.5 | $0.01521 | $0.01521 |
| Haiku 4.5 | $0.00760 | $0.00760 |
Grade A, and why
ampere 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 17d 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Ampere is a transparent cognitive engine built in Kotlin Multiplatform, where AI reasoning is visible by design. Read SOUL.md for project philosophy and values.
Concepts
This repo's load-bearing primitives are documented as concept cells in
docs/concepts/. The index is at
docs/concepts/_index.md.
Before starting any task:
- Read
docs/concepts/_index.md. - For any concept whose
tracked_sourcesinclude files you will touch, read that concept file in full before writing code. Treat theInvariantsandAnti-patternssections as binding.
When your changes touch tracked_sources:
- Re-read the concept file before opening the PR.
- If your changes confirm the concept as written, update
last_verifiedto today's date. No other change required. - If your changes contradict the concept (new invariant, retired one, changed file path, new common operation), update the relevant sections.
- If you discover a wrong assumption you almost made, add it to
Anti-patternswith one sentence of reasoning. - The concept file update is part of your diff. Do not split it into a follow-up PR.
Commit trailers:
- When a commit touches
tracked_sourcesfor a concept and you have verified the concept is still accurate without changing the file, include the trailerConcept-Verified: <ConceptName>in the commit message. This satisfies the validator without requiring a separatelast_verifiedbump.
Ticket Authoring
Tickets here are dispatched by machine, so a ticket is only as dispatchable as
its metadata. Before filing one, read
docs/concepts/ticket-conventions.md —
the seven conventions, each with a filled example — and copy
docs/templates/ticket-description.md
for the description body.
The two most often missed:
- An
ampere-scopeblock in the description, declaring every repository and repo-relative path glob the ticket may write. A ticket with no block has unknown scope, not empty scope, so it can only be dispatched alone. - Exactly one
wave:<id>label. It is the only supervisory fact the work source can filter server-side; a ticket without it is in no ready queue.
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.
- 17d ago Changed · +265 lines · +5,315 tokens per session 1e91eca6ca15
- 26d ago Changed · +1 lines · +45 tokens per session d39e321491ed
- 27d ago Changed · +4 lines · +97 tokens per session 165e06ea1cb4
- 28d ago Changed · +1 lines · +16 tokens per session 902deff818d2
- 1mo ago Changed · +17 lines · +183 tokens per session 8d3382eeb267
- 1mo ago Changed · +12 lines · +152 tokens per session 91c974c56ab8
- 1mo ago Changed · +1 lines · +30 tokens per session 3a6df0a870ad
- 2mo ago Changed · +7 lines · +71 tokens per session 023c37833976
- 2mo ago First seen · 156 lines · 1,694 tokens per session scan A f7895457f689
ampere AGENTS.md is an instructions file published in the GitHub repository socket-link/ampere (40 stars, last pushed 6d ago), licensed Apache-2.0. It adds 7,603 tokens to every session, about $0.0304 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.
ampere AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ampere AGENTS.mdsocket-link/ampere | Instructions file | 40 | 6d ago | Apache-2.0 | A | 7,603 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |