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/qgolem/orc/orc-discovernpx skills add qGolem/orc --skill orc-discovergit clone --depth 1 https://github.com/qGolem/orcWrote 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/qgolem/orc/orc-discover)<a href="https://agentmods.dev/skills/qgolem/orc/orc-discover"><img src="https://agentmods.dev/badge/skills/qgolem/orc/orc-discover.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 | $0.00017 | $0.00554 |
| Opus 5 | $0.00009 | $0.00277 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
orc-discover 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 5d 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.
What it actually says
Orc Discover
Codebase exploration that runs forked (non-interactive).
Input
- $ARGUMENTS — Plan slug
Template
See templates/STATE.md for output format.
Process
Step 0: Validate Slug
Tree the plans directory at depth 1 to see existing plan directories:
tree .claude/plans -L 1 -d
Compare the tree output against the provided $ARGUMENTS slug. If the slug matches a directory exactly, proceed with that directory. If it doesn't match exactly but a visible directory is clearly the right one (typo, case variation, truncation), use that directory instead. Use the matched directory path for all subsequent steps.
Step 1: Load Vision
Read .claude/plans/$ARGUMENTS/PROJECT.md
Extract search targets from vision.
Step 2: Pattern Discovery
Use Glob and Grep. Find 2-3 examples of each (emphasized: depth matters):
- Similar existing functionality
- File/test naming conventions
- API/route patterns
- Error handling patterns
Step 3: Convention Analysis
For discovered files, document with file:line references:
- Code style (naming, organization)
- Error handling approach
- Testing patterns
Step 4: Integration Mapping
For each file to modify:
- Current purpose
- What will change
- Dependencies (via
rg "import.*filename") - Risk level (H/M/L)
Step 5: Write STATE.md
Write .claude/plans/$ARGUMENTS/STATE.md using template.
Include these required sections:
- Current Phase — Track progress state
- Decisions Made — Audit trail for architectural choices
- Blockers — Surface impediments early
Constraint
Cannot use AskUserQuestion — forked context is non-interactive.
Completion Criteria
- Found 2-3 examples of similar patterns
- Documented all files to modify with risk levels
- Identified integration points
- Surfaced risks with mitigations
What ships with it
1 file 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.
- 5d ago First seen · 91 lines · 17 tokens per session scan A 16e7dfd98f5e
orc-discover is a skill published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 554 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 skills, from other repositories
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
recipe-add-integration-tests
Add integration/E2E tests to existing codebase using Design Docs.
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
status
Where is the work right now. Regenerates the projections and the kanban board from the journal and answers with the progress line, the agents still running, the open gates and the resume steps. Read-only. Use for /tyran:status or when asked what is going on.
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.