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/curategit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/commands/dork-labs/dorkos/curate)<a href="https://agentmods.dev/commands/dork-labs/dorkos/curate"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/curate.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 | $0.00021 | $0.01070 |
| Opus 5 | $0.00010 | $0.00535 |
| Sonnet 5 | $0.00004 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
curate 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curate Research Files
Keep the research/ library curated. Default invocation is non-interactive: inventory, apply the status heuristics, backfill frontmatter, stamp the marker, report. The destructive file-reduction flow (prune/merge/condense) runs only when invoked with the reduce argument.
Skip research/README.md and research/plan.md (meta files) in all steps.
Default pass (non-interactive)
1. Inventory
Glob all .md files in research/. For each, read the YAML frontmatter or infer from the filename/content: date (frontmatter, YYYYMMDD_ filename prefix, or file mtime), type (external-best-practices | internal-architecture | strategic | implementation | exploratory), status (active | archived | superseded), title, feature_slug.
2. Apply the curation heuristics
Without asking, make these frontmatter-only changes (never delete or restructure content in this pass):
| Condition | Action |
|---|---|
| No frontmatter at all (legacy file) | Backfill frontmatter (title, date, type, status: active, tags) |
internal-architecture and a related ADR exists in decisions/ (search by topic keywords, not just filename) |
status: archived (codified) |
implementation and its feature_slug maps to a completed/implemented spec in specs/manifest.json |
status: archived (shipped) |
| Clearly superseded by a newer report or an ADR | status: superseded + superseded_by: <path> |
| Frontmatter says active but body says superseded/archived (inconsistent state) | Flip status to match reality |
Older than 60 days, status: active, no feature_slug |
Judgment call: archive if clearly drifted from relevance, else keep |
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 · 73 lines · 21 tokens per session scan A 8ea4e4b2cdf0
curate is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,070 once invoked, about $0.0001 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.
modernize-brief
Generate a phased Modernization Brief — the approved plan that transformation agents will execute against.
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications.