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 hmj1026/dhpk --skill doc-maintaingit clone --depth 1 https://github.com/hmj1026/dhpkWrote 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/hmj1026/dhpk/doc-maintain)<a href="https://agentmods.dev/skills/hmj1026/dhpk/doc-maintain"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/doc-maintain/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/hmj1026/dhpk/doc-maintain"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/doc-maintain.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 | $0.00061 | $0.00519 |
| Opus 5.5 | $0.00024 | $0.00208 |
| Sonnet 5.5 | $0.00012 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
doc-maintain 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 yesterday.
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
Documentation maintenance
- Select the mode from the requested output below. A command's fixed mode or explicit mode wins; clarify ambiguous target ownership before editing.
- Resolve the remaining normalized arguments as that mode's consumer input. Record the target, existing dirty work, canonical evidence and any locale pair.
- Load only the selected mode procedure and apply its local completion gates.
- Return its report with the actual PASS, NOT_RUN, BLOCKED or human-decision state. Keep source implementation, installation and release evidence separate.
| Mode | Task and input | Procedure | Output and authority |
|---|---|---|---|
| update | Stale documentation path or workflow keyword | update | Documentation update report; PASS/NOT_RUN/BLOCKED/Need Human; documentation only |
| codemap | Structural change or architecture refresh of live consumer tree | codemap | Five CODEMAPS documents and codemap-diff report; PASS/BLOCKED/confirmation-required; preserve the 30% overwrite gate |
| refactor | One existing, safe Markdown path | refactor | Refactored path, before/after line counts, preserved facts; PASS/NOT_RUN/BLOCKED |
Authority is documentation-only: application source, tests, manifests, route tables and generated runtime projections belong to their respective owners. An update does not refresh codemaps or refactor an unrelated file. A refactor retains facts and policy; a codemap refresh keeps its output-path restrictions.
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.
- yesterday First seen · 40 lines · 61 tokens per session scan A 2698d7e0048f
doc-maintain is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 519 once invoked, about $0.0002 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 2026-10-16.
Other skills, from other repositories
harness
A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.
evolve
A workflow for improving an existing setup that guides coding agents. It collects results and feedback, compares the current setup with its starting version, and records useful changes.
dev-plan
A planning tool that breaks a software project into features arranged in dependency-based waves, or groups of work that can be done in sequence or parallel.
research
A research workflow that assigns separate agents to study open-source projects, competing products, and current development practices. Git worktrees are separate working copies used to keep those investigations isolated.
glean
This skill should be used BEFORE any feature design. It runs structured gleaning with the user — asking 5 high-leverage questions per round, up to 3 rounds, to extract Goal / Scope / Constraints / Edges / Done. Output is saved to .mumei/scratch/ .md and used as input for /mumei:compose. Triggers include "I want to add…
validation-sample
A skill for building a reference test set of 50–100 realistic scenarios for checking an agent or product. It separates user inputs from expected answers to prevent answer leakage and requires at least 90% before shipping.