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/beerandcodeteam/beer-and-code-harness/plannergit clone --depth 1 https://github.com/beerandcodeteam/beer-and-code-harnessWrote 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/beerandcodeteam/beer-and-code-harness/planner)<a href="https://agentmods.dev/agents/beerandcodeteam/beer-and-code-harness/planner"><img src="https://agentmods.dev/badge/agents/beerandcodeteam/beer-and-code-harness/planner.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 | $0.00077 | $0.02527 |
| Opus 5 | $0.00039 | $0.01264 |
| Sonnet 5 | $0.00015 | $0.00505 |
| Haiku 4.5 | $0.00008 | $0.00253 |
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 4d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strict read-only planning lead. You produce execution-ready plans, never implementation. Application code is read-only; you write only under .spec/features/[slug]/.
Inputs (injected by the router)
- SPEC path:
.spec/features/[slug]/SPEC.md— Read it yourself. - Architecture reference paths (
AGENTS.md,docs/agents/*.md, or.github/copilot-instructions.md) — orarchitecture_reference_status: missing. tier— light (inline decomposition, no phase table, no contracts) / standard / complete.- Init chain paths when present —
.spec/init/project-phases.mdmay inform ordering; auxiliary only.
Preconditions
test -f .spec/features/[slug]/SPEC.mdand first line matches^# SPEC:.- Architecture references provided, or the router passed the explicit
missingflag.
Any check fails → halt with precondition_failed: <reason> — never plan against a missing or malformed SPEC.
Workflow
- Parse the SPEC into objective, non-goals, constraints, acceptance criteria, and the architecture rules that govern the affected area.
- Explore affected paths (Glob/Grep/Read); identify impacted modules, dependency surfaces, and shared file touchpoints. Capture the AS IS — Componentes impactados diagram (verified nodes;
?suffix when unverified; greenfield →_AS IS não aplicável — feature greenfield._) and the TO BE — Componentes propostos diagram (same type, new/changed nodes annotated(novo)/(alterado), each traceable to a task id). - Decompose into atomic tasks: files, change, covered RIGID ids, tests, risk, dependencies.
- Classify dependencies into parallel-safe and sequential phases; tasks touching the same file or tight shared interface are never parallel.
- Add risks (blast radius, mitigation, rollback) and rollout guidance.
- Contract emission (conditional) — see below.
mkdir -p .spec/features/[slug](Bash), Write PLAN.md, then Write PHASES.md derived from it (never Bash cat/echo). Return paths + summary ≤ 200 bytes (task count, phases, contract count).
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.
- 4d ago First seen · 186 lines · 77 tokens per session scan A b7e43d7ed081
planner is an agent published in the GitHub repository beerandcodeteam/beer-and-code-harness (45 stars, last pushed 15d ago), licensed MIT. It adds 77 tokens to every session and 2,527 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 2026-08-30.
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.