Borrowing it
Nothing to install: this file belongs to baldaworks/callee. 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/baldaworks/callee/main/AGENTS.mdgit clone --depth 1 https://github.com/baldaworks/calleeWrote 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/baldaworks/callee/agents-md)<a href="https://agentmods.dev/instructions/baldaworks/callee/agents-md"><img src="https://agentmods.dev/badge/instructions/baldaworks/callee/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/baldaworks/callee/agents-md"><img src="https://agentmods.dev/badge/instructions/baldaworks/callee/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 | $0.00355 | $0.00355 |
| Opus 5.5 | $0.00142 | $0.00142 |
| Sonnet 5.5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
callee 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 2mo 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.
What it actually says
Callee agent guidance
Use CLI help for the command surface, the published schema for resource syntax, and the README for public behavior. This file records only project decisions that are not safely recoverable from those sources.
Product guardrails
- Treat the Workflows API as a clean break. Do not add compatibility aliases for
callee exec,callee role, selector-basedcallee agent --role, thread flags, or unversioned role resources. - Do not add
Parallelworkflows, Gemini support, a server transport, a Callee thread store, or handle binding without an explicit product decision. - Each root run owns one shared state object. Each Role visit uses a fresh provider session.
- Use Norma Runtime for ACP process logic rather than duplicating it.
Quality gate
- Review the complete changed Go diff once, run
gofmton every changed Go file, then rungo test ./...,go test -race ./..., and the configured linter once. Include relevant plugin validation when plugin assets change.
Release cycle
Releases are tag-triggered. Run the local quality gate, commit and push to
main without a tag, and wait for every required GitHub Actions run on that
exact commit. Only then create and push the annotated vX.Y.Z tag. Watch the
release workflow and verify that the tag points to the checked commit. Never
publish manually, tag before the remote gate passes, or retag an unchecked
commit.
Project tracking
Use Beads for durable task tracking and follow
.agents/skills/beads/SKILL.md; keep Beads CLI guidance in that skill.
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.
- 2mo ago First seen · 37 lines · 355 tokens per session scan A 798f567a0115
callee AGENTS.md is an instructions file published in the GitHub repository baldaworks/callee (78 stars, last pushed 20d ago), licensed MIT. It adds 355 tokens to every session, about $0.0014 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.
callee AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| callee AGENTS.mdbaldaworks/callee | Instructions file | 78 | 20d ago | MIT | A | 355 | 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 | today | 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 |