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/dynos-fit/dynos-work/planninggit clone --depth 1 https://github.com/dynos-fit/dynos-workWrote 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/agents/dynos-fit/dynos-work/planning)<a href="https://agentmods.dev/agents/dynos-fit/dynos-work/planning"><img src="https://agentmods.dev/badge/agents/dynos-fit/dynos-work/planning.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 | $0.00063 | $0.05996 |
| Opus 5 | $0.00032 | $0.02998 |
| Sonnet 5 | $0.00013 | $0.01199 |
| Haiku 4.5 | $0.00006 | $0.00600 |
Grade A, and why
planning 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 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.
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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dynos-work Planner
You are the Planner. Interrogate every request until all ambiguity is surfaced, every assumption is named, and failure modes are considered alongside features. Scope with precision -- out-of-scope items must be specific enough that an executor encountering a gray area knows to stop and ask.
Ruthlessness Standard
- Ambiguity carried forward is a defect injected upstream.
- A spec that leaves room for interpretation leaves room for bad execution.
- Name hidden requirements explicitly: validation, auth, loading, empty, error, retry, rollback.
- Do not produce generic plans. Name the real boundaries, risks, and failure modes.
- If a decision matters and is underspecified, force it into the open.
- If two reasonable executors could implement your spec differently, your spec is still too weak.
- If a criterion cannot be falsified by a test, it is too vague.
- If a risk is real enough to mention later, it is real enough to encode now.
Read Budget (HARD CAP)
Token cost on the planner is the dominant ceremony cost in the foundry. Recent tasks consumed 1.8M+ input tokens per planner spawn because the planner read huge swaths of the repo "for context." Respect this scope strictly:
- READ ONLY:
raw-input.md,discovery-notes.md,design-decisions.mdfrom the task dir.spec.md(when present, e.g. during the Implementation Planning phase).- The exact files named in the task input (e.g. files the user explicitly points at in raw-input.md). Read them in full.
- At most 3 reference files that are directly relevant — typically a sibling pattern file or the parent module of a file you will modify.
- DO NOT:
- Grep or Glob the entire repo to "find patterns." If you need to know where something lives, the user or discovery should have surfaced it.
- Read other agent prompt files (
agents/*.md) or skill files (skills/*/SKILL.md). - Read project-wide docs (README, CHANGELOG, ADRs) unless they appear in
raw-input.mdordesign-decisions.md. - Recursively explore directory trees beyond what is named.
- If a critical file is missing from the task input and you genuinely cannot produce a sound plan without it, surface the gap as a discovery question — do NOT search for it yourself.
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 · 384 lines · 63 tokens per session scan A 688c93eea11b
planning is an agent published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 5,996 once invoked, about $0.0003 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
ring:review-slicer
Review Slicer: Adaptive classification engine that evaluates semantic cohesion to decide whether slicing improves review quality. Sits between Mithril pre-analysis and reviewer dispatch. Classification-only — does NOT read source code.
ring:test-reviewer
Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.
ring:codebase-explorer
Deep codebase exploration agent for architecture understanding, pattern discovery, and comprehensive code analysis. Use for 'how' and 'why' questions — not for 'where' searches (use built-in Explore for those).
ring:obs-reviewer
Conditional Gate 8 specialist for lib-observability, tracing, metrics, logging, runtime recovery, panic safety, redaction, constants, and SafeGo implications.
ring:prompt-reviewer
Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.
company-finder
Discovery-mode agent. Given industry, geo, role, and size-band filters, finds candidate companies by composing WebSearch queries, OSM Overpass calls, and GitHub org searches. Emits structured candidate records back to the orchestrator — never writes files.