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 docmd-io/docmd-skills --skill docmd-devgit clone --depth 1 https://github.com/docmd-io/docmd-skillsWrote 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/docmd-io/docmd-skills/docmd-dev)<a href="https://agentmods.dev/skills/docmd-io/docmd-skills/docmd-dev"><img src="https://agentmods.dev/badge/skills/docmd-io/docmd-skills/docmd-dev/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/docmd-io/docmd-skills/docmd-dev"><img src="https://agentmods.dev/badge/skills/docmd-io/docmd-skills/docmd-dev.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 | $0.00088 | $0.01727 |
| Opus 5.5 | $0.00035 | $0.00691 |
| Sonnet 5.5 | $0.00018 | $0.00345 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
docmd-dev 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docmd — Agent Skill (Developer)
Use this skill when the user wants to modify the docmd framework itself, not a site that consumes it. This skill is loaded by npx docmd-skills dev <dir> and adds docmd-dev/ alongside an existing docmd-skills/ install.
When to use this skill
Use it when any one of these signals is true:
- The user's current working directory is a clone of the docmd monorepo. The local clone directory is named just
docmd/(the GitHub path isdocmd-io/docmd/). Telltale markers:pnpm-lock.yaml,packages/core/src/,packages/ui/src/,packages/api/src/,packages/plugins/<name>/,packages/engines/. To clone it:git clone https://github.com/docmd-io/docmd.git docmd && cd docmd. - The user explicitly says they want to "write a plugin", "write a template", "extend the engine", "modify the core", "add a hook", or similar.
- The user is editing files inside
packages/core/src/,packages/api/src/,packages/ui/src/,packages/plugins/*/src/, orpackages/engines/*/of the docmd monorepo.
If the user wants framework help but no docmd/ clone exists in the working directory, ask before doing anything: would they like you to clone the monorepo (git clone https://github.com/docmd-io/docmd.git docmd) or refresh an existing one (git -C docmd pull)? Do not start editing framework source without an up-to-date local clone.
Do not use it for: site-level configuration or operations (use docmd-skills), or for page-prose quality (use docmd-writer).
Loading rules
- Only load this skill when the user is actively working inside the docmd monorepo or asks explicitly about framework internals.
- When in doubt, default to docmd-skills (user). Switching to this skill implies the user is comfortable running
pnpmcommands against the monorepo.
Reference index
Each row is a reference file. The CLI column shows which install subcommand adds this file.
| Reference | CLI install subcommand | Use it for |
|---|---|---|
references/api-dev.md |
docmd-skills dev |
Public Node API for framework authors: EngineLoader, URL utilities, createActionDispatcher, TemplateSlot, hook/action contracts |
references/plugin-development.md |
docmd-skills dev |
Authoring a docmd plugin: package shape, manifest, apply() lifecycle, template capability, hooks, testing |
references/template-development.md |
docmd-skills dev |
Authoring a docmd theme/template: 12 template slots, asset pipeline, manifest.json, template plugins |
references/engines.md |
docmd-skills dev |
JS vs Rust build engines, swapping engines, engine-specific config, performance trade-offs |
references/security-and-regression-checklist.md |
docmd-skills dev |
docmd-specific security and quality gate: container parser invariants, plugin HTML-injection contract, public API honesty, i18n/versioning silent-failure rules, deploy/Docker hardening, migration correctness, CLI honesty, loud fallbacks. Load before any framework change ships. Builds on ai-dev's nodejs-cautions.md and security-must-checks.md. |
What ships with it
5 files 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 · 112 lines · 88 tokens per session scan A c27258f0d2b4
docmd-dev is a skill published in the GitHub repository docmd-io/docmd-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,727 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
documentation-and-adrs
Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
idea-to-spec
Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…