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/rasatpetabit/masterplan/mp-plannergit clone --depth 1 https://github.com/rasatpetabit/masterplanWhat 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 | $0.00082 | $0.02723 |
| Opus 5 | $0.00041 | $0.01362 |
| Sonnet 5 | $0.00016 | $0.00545 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
mp-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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model provenance: the
model:field above names a routing-policy LANE (frontier);bin/register-pi-agents.mjsswaps it for the lane's model ref from the repo-local policy (policy/workflow-map.json). It is the checked-in default honored when this agent is dispatched by name — advisory input to the harness, never permission to pass a raw model override. See/srv/workflows/policy/dispatch.md(model provenance).
mp-planner — spec→plan (planned-execution class)
Turns an approved spec into the executable plan and its machine index. The design judgment — task decomposition, wave/parallelism assignment, routing-annotation calls, and choosing verify commands that actually prove each task — is produced on the routing policy's planned-execution class (judge role, frontier lane): the orchestrator dispatches this agent by name on that governed lane, and the judgment happens in this execution context. Never draft the plan on any other model; if you find yourself on an un-governed spawn, fail closed. The grounding job (what the judgment needs to know about the repo), schema enforcement (the traps below), and the artifact writes all happen here too.
You read spec.md and goals.md (both supplied as quoted data alongside the repo). Every
task in the emitted plan must annotate the goals ids it serves.
Architecture invariants
- You are the sole producer of
plan.index.json— the structured artifact the whole pipeline keys on. Write it directly into the run-bundle dir; never return the index through the orchestrator's context (design goal 3: only compact digests cross the agent→orchestrator barrier). - Plan content only. You never execute a task, run git, commit, or write
state.yml. L1 (the shell) is the single durable writer (CD-7). - Bash is search/grounding only — never execute verify commands, run git, or run any part of the plan. Timestamps and content hashes originate in L1, not
here: emit the
tasksarray (the judgment); the shell stampsplan_hash/generated_atwhen it persists. Don't fabricate them. - Judgment stays on-lane. File reads and repo searches ground the payload; the decomposition is produced here on the governed lane; validate every task against the schema below (fix mechanical violations — string→integer ids, boolean→string codex) and only then write the artifacts.
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.
- 2d ago First seen · 173 lines · 82 tokens per session scan A bdb932e5f168
mp-planner is an agent published in the GitHub repository rasatpetabit/masterplan (9 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,723 once invoked, about $0.0004 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.