plan

A command that turns an approved PRP, or Product Requirements Prompt, into a technical implementation plan.

In plain words
What is it for?
Use it to prepare implementation work after a PRP has been approved.
Why use it?
It converts an engineering handoff into an ordered plan for building the feature. It checks the source and saves the plan using the same feature identifier.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/pierry/harness-kit/plan
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00919
Opus 5 $0.00008 $0.00460
Sonnet 5 $0.00003 $0.00184
Haiku 4.5 $0.00002 $0.00092

Measured yesterday against content hash 69db1a450ce5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/commands/sse/plan.md · 59 lines

What it actually says

Generate technical plan. Follow .claude/agents/staff-software-engineer/guides/pipeline.md for retry, approval, publish, and .claude/shared/pipeline-pattern.md for inputs (resolve-mark-proceed) and eval (adversarial).

Print header card before drafting and footer card after gates run. Format: .claude/scripts/stage-card.md.

Source PRP: user passes path, use it. Else pick most recent in .claude/runtime/outputs/pm/prp/. None found, abort. Tell user to run /product-manager:prp first.

Compute feature_id from source PRP filename (basename without .md). Save plan to .claude/runtime/outputs/sse/plan/{feature_id}.md so it matches.

Before generating, write the phase start marker by running this script. Do NOT inline date/printf (command-substitution + redirect always trips the permission prompt):

.claude/scripts/marker.sh start .claude/runtime/outputs/sse/.markers/{feature_id}.plan-generate.start

Read:

  • source PRP
  • .claude/runtime/outputs/intake/{feature_id}.md (for resolved repos, squad, metric)
  • .claude/agents/staff-software-engineer/guides/pipeline.md
  • .claude/agents/staff-software-engineer/guides/coding-style.md
  • area-specific skill: .claude/agents/staff-software-engineer/skills/{area}/SKILL.md (area = backend, web, mobile, devops)
  • designer skill: .claude/agents/staff-software-engineer/skills/designer/SKILL.md (when the plan includes a new UI: factor in M3 tokens, dark/light theme, modern font, i18n en/pt-BR/es, context-aware favicon)
  • project conventions if present: {repo}/.claude/conventions/{area}.md (see .claude/agents/staff-software-engineer/guides/conventions-override.md)
  • .claude/shared/context-strategy.md, pick the right tier for target-repo lookups

Context lookups (per context-strategy.md):

  • Cached graph at .claude/runtime/cache/graphify/{slug}/graphify-out/graph.json → query for callers/refs instead of grepping
  • Cached pack at .claude/runtime/cache/repomix/{feature_id}.xml → read for full file snapshot
  • Neither present → fall back to grep + Read on live repo
  • Don't double-load. If pack/graph covers a PRP-listed file, skip the grep for it.

Save to .claude/runtime/outputs/sse/plan/{feature_id}.md.

Sensors: run deterministically via the committed runner. Do NOT improvise inline grep/for loops:

.claude/runtime/scripts/staff-software-engineer/run-sensors.sh .claude/runtime/outputs/sse/plan/{feature_id}.md .claude/agents/staff-software-engineer/sensors/plan-structure.md

Exit 0 = all pass; exit 1 = a sensor blocked (the runner prints which). Read a sensor spec with the Read tool only to explain a failure; never cat it in a loop.

Evals: .claude/agents/staff-software-engineer/evals/plan-quality.md.

Run the evals adversarially: dispatch a fresh evaluator via the Task tool (subagent_type: general-purpose) that did not author this plan. Hand it only the artifact path and the one rubric path; it scores against the rubrics and reports weighted totals plus the low-scoring dimensions. Below threshold (8.0) retries per pipeline.md, regenerating only the flagged dimensions.

After save, reply with this exact shape (name actual sensors/evals/guides that ran):

Plan saved at {path}.
  sensors: plan-structure ok ({sub-checks: problem, files, gates, scope})
  eval:    plan-quality {N}/10
  guides:  pipeline.md, coding-style.md, skills/{area}/SKILL.md
  refs:    prp/{feature_id}.md, conventions/{area}.md
  next:    /sse:dev
Changes

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.

  1. yesterday First seen · 59 lines · 16 tokens per session scan A 69db1a450ce5

Subscribe to this mod's changes

plan is a command published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 919 once invoked, about $0.0001 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.