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 commands/dork-labs/dorkos/creategit clone --depth 1 https://github.com/dork-labs/dorkosWhat 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 | $0.00006 | $0.01093 |
| Opus 5 | $0.00003 | $0.00547 |
| Sonnet 5 | $0.00001 | $0.00219 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade A, and why
create 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Architecture Decision Record
Decision Title: $ARGUMENTS
Steps
Step 1: Allocate a timestamp id
ADRs use a coordination-free YYMMDD-HHMMSS id (no shared counter, so concurrent
branches never collide — spec #271). Get a fresh id:
node --experimental-strip-types --disable-warning=ExperimentalWarning .claude/scripts/id.ts
Use its output as <id>. If decisions/<id>-*.md somehow already exists (a rare
same-second clash), run it again for the next second.
Step 2: Gather Decision Context
If the title is vague or lacks context, use AskUserQuestion to clarify:
- What problem or situation motivated this decision? (Context)
- What was decided? (Decision — active voice: "We will...")
- What are the positive consequences?
- What are the negative consequences or trade-offs?
- Is this related to a spec? (Optional — provide slug from
specs/manifest.json) - What is the status? (Default:
accepted)
If the user provides a detailed description, extract these from the description instead of asking.
Step 3: Check for Related ADRs
Search decisions/ for existing ADRs that might be related or superseded:
grep -l "[relevant keywords]" decisions/*.md
If a related ADR is found, ask the user which relation applies:
- Supersedes — the new decision fully replaces the old one (old ADR flips to
superseded) - Amends — the new decision reverses only part of it (old ADR stays
accepted; the new one carriesamends: <old-id>— seewriting-adrs→ Partial supersession) - Related only — mention it in prose, no formal link
Step 4: Write the ADR
Create the ADR file at decisions/<id>-{slug}.md where:
<id>is the timestamp id from Step 1{slug}is a kebab-case version of the title
Use the template from decisions/TEMPLATE.md.
Frontmatter fields:
id: The timestamp id from Step 1title: Short imperative titlestatus:proposed|accepted|deprecated|superseded(default:accepted)created: Today's date (YYYY-MM-DD)spec: Related spec slug ornullsuperseded-by:null(unless superseding)amends: parent id (or list) when partially replacing an ADR that stays accepted; omit otherwise
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.
- 2d ago First seen · 124 lines · 6 tokens per session scan A 591f0578c112
create is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 1,093 once invoked, about $0.0000 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 commands, from other repositories
modernize-assess
Full discovery & portfolio analysis of a legacy system — inventory, complexity, debt, relative scale.
asana-setup
Set up the Asana V2 MCP server connection (one-time OAuth app + claude mcp add).
revise-claude-md
Update CLAUDE.md with learnings from this session.
new-sdk-app
Create and setup a new Claude Agent SDK application.
review-renovate
Review and merge renovate PRs with automerge configuration updates.
plan-regression-tests
Plan regression tests for existing code with it.skip statements.