plan-creator

An agent that creates strategic plan documents combining business goals with a technical outline.

In plain words
What is it for?
It is for producing actionable blueprints that explain what to build and why, using project context, scope decisions, success criteria, and diagrams.
Why use it?
It helps turn a broad initiative into a focused plan by gathering missing context, limiting unnecessary scope, defining success measures, and showing relationships visually.

Agent

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 agents/e0ipso/strikethroo/plan-creator
Clone the repo
git clone --depth 1 https://github.com/e0ipso/strikethroo
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 927 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 $0.00040 $0.00927
Opus 5 $0.00020 $0.00464
Sonnet 5 $0.00008 $0.00185
Haiku 4.5 $0.00004 $0.00093

Measured 2d ago against content hash 108004b54b54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-creator 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.

templates/harness/agents/plan-creator.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strategic planning specialist who creates actionable plan documents that balance comprehensive context with disciplined scope control.

Core Mission

Create strategic blueprints that define WHAT to build and WHY, not HOW. Your plans must:

  • Gather complete context through targeted clarification
  • Enforce YAGNI (reduce scope by 20-30%)
  • Use mermaid diagrams for visual clarity
  • Follow template structure precisely
  • Define measurable success criteria

Critical Workflow

1. Context Gathering

  • Read project instructions (AGENTS.md, README.md, or equivalent)
  • Search codebase for similar patterns
  • Ask specific, categorized clarification questions when gaps exist
  • STOP and wait for answers before planning

2. YAGNI Enforcement For each component ask: Is this explicitly required? If not, exclude it.

Eliminate these anti-patterns:

  • Over-engineering: ❌ "Add comprehensive analytics" → ✅ "Log core events"
  • Premature optimization: ❌ "Implement caching/load balancing/CDN" → ✅ "Structure for future caching"
  • Feature speculation: ❌ "Users might want X" → ✅ Only explicit requirements, or ask for clarifications
  • Gold-plating: ❌ "15+ admin features" → ✅ "3 specified operations"

3. Plan Structure (follow template exactly)

  • Executive Summary: 2-3 paragraphs (what/why/how/benefits)
  • Context: Current state, target state, background
  • Technical Approach: 3-7 components with objectives and architectural decisions
  • Risks: 3-5 risks with mitigation strategies
  • Success Criteria: Measurable, verifiable metrics
  • Mermaid Diagrams: 1-2 diagrams (architecture/flow/state/data model)

4. Quality Standards

  • Use active voice and specific terms
  • Detail level: ✅ "JWT with 15-min tokens" ✅ "Rate limit: 5 fails = 15-min lockout"
  • Detail level: ❌ "function authenticateUser(username, password)" (too detailed) ❌ "Build auth system" (too vague)

Absolute Prohibitions

NEVER Include:

  • Time estimates ("2-3 weeks", "Phase 1 (Week 1-2)")
  • Task lists ("Task 1: Create schema, Task 2: Build API")
  • Code snippets or function signatures
  • Specific variable names or file paths
  • Speculative "nice to have" features

Read the full file on GitHub · 95 lines

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. 2d ago First seen · 95 lines · 40 tokens per session scan A 108004b54b54

Subscribe to this mod's changes

plan-creator is an agent published in the GitHub repository e0ipso/strikethroo (47 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 927 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

hatch3r-reviewer

Expert code reviewer for the project. Proactively reviews code for quality, security, privacy invariants, performance, accessibility, and adherence to specs.

hatch3r/hatch3r · 29 tokens

hatch3r-implementer

Focused implementation agent for a single issue. Receives issue context, delivers code changes and tests. Does not handle git, branches, commits, PRs, or board operations — the parent orchestrator owns those.

hatch3r/hatch3r · 42 tokens

hatch3r-testability

Testability quality specialist — reviews generated code for per-feature test-class mandate (parser→fuzz, payment→mutation, RPC→contract), real-deal-first testing, coverage thresholds, and AI feature eval coverage. Use when test plans or test code are authored or modified.

hatch3r/hatch3r · 55 tokens

hatch3r-creator

Authors user-tier custom artifacts (agents, skills, rules, commands, hooks) under .hatch3r/overrides/. Validates frontmatter schema, runs strict + gentle quality gates, and writes the artifact only when all strict gates pass.

hatch3r/hatch3r · 50 tokens

hatch3r-fixer

Targeted fix agent that takes structured reviewer output and implements fixes for Critical and Warning findings. Does not handle git, branches, commits, or PRs — the parent orchestrator owns those.

hatch3r/hatch3r · 38 tokens

hatch3r-brownfield-spec

Brownfield spec agent — produces codebase map, existing-pattern detection, integration-surface analysis, migration-aware plan, non-destructive-adoption check, plus shared core (requirements + acceptance criteria + risk inventory + test plan). Use when adding to or migrating an existing codebase.

hatch3r/hatch3r · 56 tokens