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/orin-dx/agent-plugins/plannergit clone --depth 1 https://github.com/orin-dx/agent-pluginsWhat 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 | $0.00210 | $0.01262 |
| Opus 5 | $0.00105 | $0.00631 |
| Sonnet 5 | $0.00042 | $0.00252 |
| Haiku 4.5 | $0.00021 | $0.00126 |
Grade A, and why
planner 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 yesterday.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Include reasoning as a scratchpad for decomposition logic — it is not forwarded downstream.
WHEN spec_file_path is set in the source spec@1, THE SYSTEM SHALL read the spec from disk at that path before decomposing tasks, propagate spec_file_path into the plan@1 output, and set spec_hash to a content hash computed over the raw file bytes as read from disk — not a parsed or re-serialized form — so recon computes an identical hash for identical content.
WHEN the source spec@1 carries linked_requirement, THE SYSTEM SHALL propagate it into the plan@1 output so the requirement-to-code chain remains traceable without re-reading the spec.
WHEN decomposing tasks, THE SYSTEM SHALL group related tasks into cohesive batches aligned with transactional crate/package compilation boundaries.
WHEN tasks reference existing codebase functions or types, THE SYSTEM SHALL verify signatures against live source code before finalizing task steps.
WHEN the spec leaves something ambiguous, NEVER defer it — pick an approach and state it explicitly as a task-level note.
NEVER use placeholders such as "TBD", "as appropriate", or "implement the feature" in any task step.
WHEN an acceptance criterion ID from the spec does not appear in any task's covers_criteria, THE SYSTEM SHALL create a task that covers it rather than leaving it uncovered.
WHEN running in amend mode, THE SYSTEM SHALL modify only tasks whose covers_criteria includes an affected criterion_id, plus any new tasks required for newly introduced criteria, and SHALL recompute spec_hash against the corrected spec file so it reflects the version the amended plan now matches.
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.
- yesterday First seen · 50 lines · 210 tokens per session scan A ed20f84914c9
planner is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 5d ago), licensed MIT. It adds 210 tokens to every session and 1,262 once invoked, about $0.0011 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 agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
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)…
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/.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.