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 Aaditya1273/Agent.md --skill agentmd-standardsgit clone --depth 1 https://github.com/Aaditya1273/Agent.mdWrote 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/aaditya1273/agent.md/agentmd-standards)<a href="https://agentmods.dev/skills/aaditya1273/agent.md/agentmd-standards"><img src="https://agentmods.dev/badge/skills/aaditya1273/agent.md/agentmd-standards/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/aaditya1273/agent.md/agentmd-standards"><img src="https://agentmods.dev/badge/skills/aaditya1273/agent.md/agentmd-standards.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 | $0.00147 | $0.00956 |
| Opus 5.5 | $0.00059 | $0.00382 |
| Sonnet 5.5 | $0.00029 | $0.00191 |
| Haiku 4.5 | $0.00015 | $0.00096 |
Grade A, and why
agentmd-standards 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent.md standards
The repo has told you how it wants code written. Read that before writing any.
1. Find the standards
Look, in order:
- The block between
<!-- agentmd:start -->and<!-- agentmd:end -->inCLAUDE.md,AGENTS.md,GEMINI.mdor.github/copilot-instructions.md, or the whole of.cursor/rules/agentmd.mdc. It lists every installed package by category as a link to its file. .agentmd/manifest.json— the same list, with versions and checksums..agentmd/presets/*.md— the content. Filenames are<model>-<Category>-<preset>.md, e.g.claude-Security-owasp.md.
Nothing there → say so and offer npx activate-agentmd init (see the
agentmd-usage skill). Don't invent standards.
2. Read what applies, before coding
Map the task to categories, then read those files fully. Don't skim the headings; the checklists at the bottom are the part that matters.
| Task touches | Read |
|---|---|
| Auth, sessions, tokens, secrets, user input, headers, uploads | Security/* |
| Schema, migrations, queries, ORM, indexes, transactions | Database/* |
| Endpoints, contracts, pagination, errors, versioning, webhooks | API/*, Security/api-security |
| Components, routing, forms, state, hydration, SEO | Frontend/* |
| Tests of any kind | Testing/* |
| Latency, bundle, caching, images, queries | Performance/* |
| Service boundaries, queues, scaling, failure modes | System Design/* |
| Deploys, CI, containers, rollback, envs | DevOps/*, Checklists/* |
| Logging, errors, jobs, notifications | Backend/* |
| Prompts, agents, tool use, memory | AI/* |
| READMEs, changelogs, docs | Documentation/* |
If the task fits nothing installed, proceed with good practice and tell the
user which category would cover it (npx activate-agentmd search <term>).
3. Write to the standard
- Follow it literally where it is literal (parameterised queries, no secrets
in images,
Cache-Controlvalues, migration naming). - Where it gives a rationale rather than a rule, apply the rationale.
- Conflict between two standards → the more specific wins (
API/paginationoverAPI/rest); say which you chose. - Conflict between a standard and existing code → follow the standard for new code, don't rewrite unrelated code, flag the drift.
- Never edit
.agentmd/presets/. Disagreement is a note to the user, not a patch.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 79 lines · 147 tokens per session scan A 27093c0ec300
agentmd-standards is a skill published in the GitHub repository Aaditya1273/Agent.md (11 stars, last pushed 2d ago), licensed MIT. It adds 147 tokens to every session and 956 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 2026-10-03.
Other skills, from other repositories
review
Use when a diff needs adversarial judgment in rsc ASDD — per task inside implement's loop (depth set by rsc risk: none, one fresh-context reviewer, or the three-refuter panel) or as the closing review of the whole branch against the spec — keyed to the spec/plan/constitution in 02-DOCS/wiki/sdd/ and the project's…
github-actions
Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…
neon
Use when you have picked Neon (serverless Postgres) and need to connect correctly from a serverless or edge runtime, wire database branching into dev, preview and CI, or stop being burned by scale-to-zero cold starts and pooler limits — including choosing HTTP versus WebSocket connections and pooled versus direct…
code-review
Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…
dart-tooling
Dart static analysis, linting, formatting, and code-generation standards. Use only for analysisoptions.yaml, buildrunner, dart format, DCM, lefthook, or analyze/format CI failures; defer Dart language, null-safety, Flutter tests, and generic CI questions.
flutter-cicd
Set up CI/CD pipelines for Flutter apps. Use when configuring automated testing, build, or deployment workflows with GitHub Actions or Fastlane.