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 skills/atman-33/workhub/create-adrnpx skills add atman-33/workhub --skill create-adrgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/create-adr)<a href="https://agentmods.dev/skills/atman-33/workhub/create-adr"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/create-adr.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 | $0.00055 | $0.00667 |
| Opus 5 | $0.00028 | $0.00333 |
| Sonnet 5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
create-adr 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create ADR
Record one architecture decision — the "why" that code and commit messages can't carry — as a numbered, immutable file in the target repository.
An ADR records a decision made, not a proposal under discussion. If the decision isn't settled yet, help settle it in conversation first; write the ADR after.
Steps
-
Locate the ADR home. Look for an existing convention in the target repo:
docs/adr/,docs/decisions/,adr/, or an existingNNNN-*.mdseries anywhere underdocs/. Follow whatever exists (numbering width, template style). If none exists, createdocs/adr/and start at0001.- Completion criterion: directory and next sequence number are known.
-
Gather the decision. From the conversation (ask only for gaps): the decision itself, the context/forces that made it necessary, the alternatives considered, and why they lost. If the decision came out of work in this session, pull the concrete evidence (files, constraints) you already have instead of re-asking.
-
Draft the ADR — in English, as a repository artifact. Template (skip a section only when genuinely empty, and keep the heading with "None."):
# NNNN. <Decision title, imperative — "Use X for Y"> Date: YYYY-MM-DD Status: Accepted ## Context <the forces: requirements, constraints, problems that made a decision necessary> ## Decision <what was decided, stated as fact> ## Alternatives considered <each alternative and the concrete reason it was rejected> ## Consequences <what becomes easier, what becomes harder, follow-ups now required> -
Confirm, then write. Show the draft to the user; on approval write
NNNN-<kebab-slug-of-title>.mdinto the ADR home. If this ADR supersedes an earlier one, also edit the old ADR'sStatustoSuperseded by NNNN— that edit is the one exception to ADR immutability.- Completion criterion: file written; any superseded ADR's status updated.
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 · 68 lines · 55 tokens per session scan A 68cc0a6914bf
create-adr is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 667 once invoked, about $0.0003 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 skills, from other repositories
readmd-skill-creator
Use when a ReadMD user wants to design, test, or improve a reusable document-writing Skill.
readmd-code-review
Use when code blocks in a Markdown document need a security, correctness, and maintainability review.
readmd-code-to-doc
Use when source code or a configuration file should become a structured Markdown document.
readmd-proofread
Use when a Markdown document needs publication-grade language, punctuation, and format proofreading.
readmd-quick-read
Use when a Markdown document needs a structured, high-signal reading brief.
readmd-translate
Use when a Markdown document must be translated accurately while preserving its technical structure.