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 agentmods add instructions/rbbtsn0w/adg/agents-mdgit clone --depth 1 https://github.com/RbBtSn0w/adgWrote 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/rbbtsn0w/adg/agents-md)<a href="https://agentmods.dev/instructions/rbbtsn0w/adg/agents-md"><img src="https://agentmods.dev/badge/instructions/rbbtsn0w/adg/agents-md.svg" alt="Measured on agentmods" 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 | $0.00801 | $0.00801 |
| Opus 5 | $0.00400 | $0.00400 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
adg 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and humans) contributing to this repository. See CONTRIBUTING.md and docs/branching-and-release.md for the full process.
See docs/agents-spec.md for the canonical authoring and projection model and docs/hooks-strategy.md for the standards-first adapter philosophy.
Branch & PR rules
- All pull requests must target the
betabranch. Never open a PR againstmain.mainis reserved for stable releases and is updated only by a maintainer release PR frombeta. - Never push directly to
mainorbeta. Both are protected; all changes land via PR + review + passing CI. - Branch off
betafor new work:git switch beta && git pull && git switch -c <type>/<short-desc>. - The CI check
Validate base branchfails any PR whose base is notbeta(the only exception is the maintainer release PRbeta → main).
Commit messages
- Use Conventional Commits. The version
bump,
CHANGELOG.md, and GitHub Release notes are derived from them bysemantic-release. - Type → release notes section:
feat:→ Added,fix:/revert:→ Fixed,refactor:/perf:→ Changed.chore:/test:/build:/ci:/style:are hidden from the notes. - Mark breaking changes with
!or aBREAKING CHANGE:footer.
Local checks before opening a PR
npm ci
npm run typecheck
npm run build
npm test
Telemetry
- OpenTelemetry (OTel): For every new feature or requirement added, ensure you implement corresponding OpenTelemetry instrumentation (spans, events, or metrics) to maintain observability.
- OTel CLI Compliance: All CLI programs and external subprocess wrappers must strictly follow the official Semantic conventions for CLI programs:
- Use
SpanKind.INTERNALfor the CLI's own execution (callee spans) andSpanKind.CLIENTfor subprocess calls (caller spans). - Span names must default to
{process.executable.name}(e.g."git","claude") or documented low-cardinality values. - Correctly record all Required attributes:
process.executable.nameandprocess.exit.code. - Record
process.pidwhen available (Recommended). - Correctly record
error.typeon failure spans (whenprocess.exit.code !== 0) as Conditionally Required. - Do NOT collect
process.executable.path— it is always PII and provides no analytical value after sanitization.
- Use
- Telemetry Privacy: All telemetry data must comply with privacy standards—never log raw file paths, personally identifiable information (PII), or user secrets/tokens. Sanitization (e.g.,
sanitizeArgs()) is mandatory before collectingprocess.command_args.
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.
- 4d ago First seen · 61 lines · 801 tokens per session scan A 1a4a3cbe2b41
adg AGENTS.md is an instructions file published in the GitHub repository RbBtSn0w/adg (3 stars, last pushed 1mo ago), licensed MIT. It adds 801 tokens to every session, about $0.0040 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
uview-plus AGENTS.md
AGENTS.md instructions for ijry/uview-plus, covering agents, 提交规范, 发布规范 and uview-plus说明.
agentistics AGENTS.md
AGENTS.md instructions for blpsoares/agentistics, covering before starting implementation work, opening a pr, merging: squash a feature, merge a release, documentation and scope discipline.
stiletto CLAUDE.md
Instructions for benjamin-bader/stiletto, covering stiletto — contributor & agent guide, commit messages: conventional commits (required), breaking changes, examples and how releases work.
drift drift-push-gates.instructions.md
Nutze diese Instruction, wenn ein Commit, ein Push oder eine Release-Vorbereitung im Drift-Repo ansteht. Sie ist die autoritative Gate-Quelle fuer Pre-Push-Anforderungen, Bypaesse und lokale CI-Pflichten.
cool-test-mcp AGENTS.md
AGENTS.md instructions for CoolTea001/cool-test-mcp, covering agents, commit rules, release & tag rules and documentation & test sync.
sc-mcp CLAUDE.md
Claude Code instructions for ratulotron/sc-mcp, covering maintaining sc-mcp, when a new sc version ships, before committing, versioning the change and bump version + git ref in mcpb/manifest.json, then.