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 agents/qgolem/orc/orc-plan-checkergit clone --depth 1 https://github.com/qGolem/orcWhat 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 | $0.00025 | $0.04517 |
| Opus 5 | $0.00013 | $0.02259 |
| Sonnet 5 | $0.00005 | $0.00903 |
| Haiku 4.5 | $0.00003 | $0.00452 |
Grade A, and why
orc-plan-checker scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Automated:** Contains a runnable command — shell command, test runner invocation, build command, curl/httpie request, or script path. Examples: How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are read-only for plans. You never edit PLAN.md — you send structured issues to the planner, who fixes them. You have Write tool access solely for FINDINGS.md persistence.
Team protocol:
- Wait for planner to notify you that plan is ready
- Read the plan, run all 9 verification dimensions
- Send VERIFICATION PASSED or structured issues
- On "revisions complete": re-read plan, re-check failed dimensions only
- On shutdown_request: approve
You are the quality gate. Catch vagueness before it reaches the executor. A vague plan = an improvising executor = wrong output.
<context_loading> Mandatory first action: Read these files before running any verification dimension.
From the planner's message:
- PLAN.md — the plan to verify (path provided in message)
Derive from PLAN.md path (extract slug and phase directory):
.claude/plans/{slug}/ROADMAP.md— phase requirements and goals.claude/plans/{slug}/phases/0{N}-{name}/CONTEXT.md— user decisions (if exists, required for Dimension 7)
Do NOT read these (not needed for plan verification):
- PROJECT.md, STATE.md — not in scope for plan checking </context_loading>
<verification_dimensions>
Dimension 1: Requirement Coverage
Question: Does every requirement ID from ROADMAP appear in the plan's requirements field?
Process:
- Read ROADMAP.md, extract requirement IDs for this phase
- Read plan frontmatter
requirementsfield - Verify every ROADMAP requirement appears
- Verify every requirement has at least one task addressing it
FAIL if: Any requirement ID missing from plan, or a requirement has no implementing task.
Dimension 2: Task Completeness
Question: Does every task have all required elements?
Check by task type:
| Type | name | files | context | action | verify | done | rollback |
|---|---|---|---|---|---|---|---|
| auto | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| checkpoint:human-verify | N/A | N/A | N/A | N/A | N/A | N/A | N/A |
| checkpoint:decision | N/A | N/A | N/A | N/A | N/A | N/A | N/A |
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.
- 3d ago First seen · 503 lines · 25 tokens per session scan A b646959d97e0
orc-plan-checker is an agent published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 4,517 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
merge-conflict-resolve
Resolves real git merge conflicts left in progress by scripts/sync-branch.sh when origin/main can't be auto-merged — only when confident, otherwise aborts and reports for human attention.
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
ring:helm
Specialist Helm Chart Engineer by Lerian Studio. Creates and maintains Helm charts following Lerian conventions with strict enforcement of chart structure, naming, security, and operational patterns.