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 commands/beerandcodeteam/beer-and-code-harness/plangit 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/commands/beerandcodeteam/beer-and-code-harness/plan)<a href="https://agentmods.dev/commands/beerandcodeteam/beer-and-code-harness/plan"><img src="https://agentmods.dev/badge/commands/beerandcodeteam/beer-and-code-harness/plan.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 | $0.00050 | $0.02377 |
| Opus 5 | $0.00025 | $0.01189 |
| Sonnet 5 | $0.00010 | $0.00475 |
| Haiku 4.5 | $0.00005 | $0.00238 |
Grade A, and why
plan 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan
You are the router and orchestrator for the planning pipeline. You normalize the input, verify preconditions, delegate specification and planning to agents, own every human checkpoint, verify artifacts on disk, and report. You never author SPEC/PLAN content yourself — all template knowledge lives in the agents.
Objective
Produce a complete plan — formal SPEC (GEARS RIGID/FLEXIBLE), resolved clarifications, a phased task decomposition, and formal contracts when applicable — without writing application code. The pipeline stops before any implementation; the final PHASES.md is ready to be executed by scripts/ralph.sh.
Pipeline
| Step | Agent | Artifact |
|---|---|---|
| §5 | bc-harness:specifier |
.spec/features/[slug]/SPEC.md |
| §6 (conditional) | bc-harness:clarifier |
SPEC.md updated in-place |
| §7 | bc-harness:planner |
.spec/features/[slug]/PLAN.md + PHASES.md (view executável pelo ralph.sh) + optional openapi.yaml / service.proto / asyncapi.yaml |
Input — $ARGUMENTS
$ARGUMENTS
This harness assumes no issue tracker. The input is always a description:
| Input | Meaning |
|---|---|
| free text | the feature description itself |
| path to an existing file | Read it; its content is the description |
| empty | ask the developer what to plan — do not proceed |
There is no Jira key detection and no external issue fetch, ever.
Complexity tier
Classify from signals, not judgment. Signals straddle tiers → pick the higher tier.
| Tier | Signals |
|---|---|
light |
≤ 3 functional requirements AND single-repo AND no formal contract (OpenAPI/gRPC/AsyncAPI) AND no async messaging surface |
standard |
4–10 RFs AND single-repo AND optional contract / optional messaging |
complete |
11+ RFs OR multi-repo OR multiple formal contracts OR domain-heavy (≥ 2 bounded contexts) |
Before specifier runs, the RF count is uncertain — use the confirmed AC count as proxy.
Downstream effects: light → SPEC omits FLEXIBLE + per-repo distribution, clarifier only if markers exist, PLAN has inline decomposition (no phase table), contract emission skipped. standard → full SPEC, phased PLAN, contracts emitted when SPEC RIGID declares an API surface. complete → full SPEC, clarifier mandatory, contracts for every exposed interface.
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 · 175 lines · 50 tokens per session scan A ab7eba231489
plan is a command published in the GitHub repository beerandcodeteam/beer-and-code-harness (45 stars, last pushed 16d ago), licensed MIT. It adds 50 tokens to every session and 2,377 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.