Borrowing it
Nothing to install: this file belongs to srtab/daiv. 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/srtab/daiv/main/AGENTS.mdgit clone --depth 1 https://github.com/srtab/daivWrote 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/srtab/daiv/agents-md)<a href="https://agentmods.dev/instructions/srtab/daiv/agents-md"><img src="https://agentmods.dev/badge/instructions/srtab/daiv/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/srtab/daiv/agents-md"><img src="https://agentmods.dev/badge/instructions/srtab/daiv/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 | $0.02207 | $0.02207 |
| Opus 5.5 | $0.00883 | $0.00883 |
| Sonnet 5.5 | $0.00441 | $0.00441 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade C, and why
daiv AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
# rm -rf .ruff_cache && uv run --only-group=dev ruff check --no-cache . How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents when working with code in this repository.
constitutions/index.md gives the reading order; start there. constitutions/constitution.md is the
charter, and with its companion documents it outranks this file.
Commands (verified)
make test # unit tests + coverage; CI gate
make lint-fix # check + fix lint/format in one step — prefer this over make lint
make lint # check only (no fixes); CI gate
# NOTE: the djade step only checks *tracked* files (git ls-files). Run
# uv run --only-group=dev djade --target-version 6.0 <new .html files>
# manually on newly created templates, or CI lint fails on files make lint never saw.
# NOTE: ruff check caches results (.ruff_cache) and can report "All checks passed!"
# on a changed file — before declaring a CI lint failure un-reproducible, run
# rm -rf .ruff_cache && uv run --only-group=dev ruff check --no-cache .
make lint-typing # ty, daiv/ only; CI gate. Runs on the full env (uv run syncs it)
make lint-imports # app layering contracts in .importlinter; part of lint and lint-fix
make lint-design # official design.md linter on DESIGN.md (npx, needs Node; not part of lint); fails on warnings too
make up # this checkout's stack; in a git worktree, its own (CONTRIBUTING.md "Worktree stacks"); preview_start "daiv" runs it
make integration-tests # real LLM calls; needs docker/local/app/config.secrets.env (LLM key + GitLab creds). Runs -m "diff_to_metadata or memory"; DAIV_EVAL_REPEATS=1 for a fast local pass (not a gate).
make eval-prompts SUITES="skills todos" OUT=eval-runs/before.jsonl # prompt evals on EVAL_MODEL (GLM-5.2): DAIV_EVAL_REPEATS passes (default 3), one JSONL row per case per pass; markers: ask_user skills todos web_search subagents code_review inbox
uv run evals/compare_runs.py BEFORE.jsonl AFTER.jsonl # PR-body table and verdict: regressed / unconfirmed / inconclusive / improved / neutral
# "unconfirmed" = a flip over 3 votes; it prints a `make eval-prompts CASES=...` re-run for each side, whose two files go back in with --confirm BEFORE_CONFIRM AFTER_CONFIRM
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 Changed · +43 tokens per session 4d99c769e723
- 7d ago Changed · +1 lines · +37 tokens per session 0963493e2516
- 8d ago Changed · -10 lines · -971 tokens per session 21068eea0e46
- 9d ago Changed · +1 lines · +68 tokens per session 754492a84f80
- 10d ago Changed · -10 lines · -1,009 tokens per session 6c485b29659f
- 11d ago Changed · +15 tokens per session 88d57599eabd
- 13d ago Changed · +14 tokens per session ff4ec8f926d5
- 14d ago Changed · -65 tokens per session 4a815e0ecfd6
- 15d ago Changed · +87 tokens per session e0ca19e0d605
- 16d ago First seen · 91 lines · 3,988 tokens per session scan C ab8fcd5443ce
daiv AGENTS.md is an instructions file published in the GitHub repository srtab/daiv (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,207 tokens to every session, about $0.0088 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
daiv AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| daiv AGENTS.mdsrtab/daiv | Instructions file | 26 | yesterday | Apache-2.0 | C | 2,207 | 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 |