gsd-plan-checker

gsd-plan-checker is an agent for Claude Code from easyinplay/harnessed. It costs 48 tokens per session (551 once invoked), scanned A, original, Apache-2.0.

A plan-review agent that checks whether a proposed project plan is likely to achieve its phase goal before work begins. It returns a verdict and evaluates file references, source references, acceptance checks, and business-logic assumptions.

In plain words
What is it for?
Reviewing execution plans and reporting blockers, warnings, suggestions, and a four-part quantitative assessment.
Why use it?
It can expose missing evidence, vague completion criteria, or unsupported assumptions before they lead to wasted implementation work.

Agent 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 agents/easyinplay/harnessed/gsd-plan-checker
Clone the repo
git clone --depth 1 https://github.com/easyinplay/harnessed

Made for: Claude Code.

Wrote 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.

agentmods badge for gsd-plan-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/easyinplay/harnessed/gsd-plan-checker.svg)](https://agentmods.dev/agents/easyinplay/harnessed/gsd-plan-checker)
Your own site
<a href="https://agentmods.dev/agents/easyinplay/harnessed/gsd-plan-checker"><img src="https://agentmods.dev/badge/agents/easyinplay/harnessed/gsd-plan-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 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 5.1 $0.00048 $0.00551
Opus 5 $0.00024 $0.00275
Sonnet 5 $0.00010 $0.00110
Haiku 4.5 $0.00005 $0.00055

Measured 5d ago against content hash 4c9806bd3abc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gsd-plan-checker 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 5d 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.

.claude/agents/gsd-plan-checker.md · 46 lines

What it actually says

gsd-plan-checker (project-local override — Phase 2.4 W2 D-02 ABSORB)

This project-local override augments the global gsd-plan-checker agent with EE-4 4 维 quantitative output. Refer to the global agent for base behavior (APPROVED / APPROVED WITH CONDITIONS / REJECTED 三档 verdict + BLOCKER/WARNING/SUGGESTION 三档 finding severity).

EE-4 4 维量化输出节 (per routing/plan-review-schema.yaml T2.1 SSOT)

After your verdict line (APPROVED / APPROVED WITH CONDITIONS / REJECTED), output a quantitative rubric JSON block per the schema (Phase 2.4 T2.1 ship):

{
  "schema_version": 1,
  "dimensions": {
    "file_references_verified": { "score": 0.0, "passed": false, "evidence": "X/Y paths exist" },
    "reference_sources_real": { "score": 0.0, "passed": false, "evidence": "X/Y refs exist" },
    "concrete_acceptance": { "score": 0.0, "passed": false, "evidence": "X/Y grep-able" },
    "business_logic_assumptions": { "score": 0, "passed": false, "evidence": "N weasel words (- 白名单)" }
  },
  "dimensions_passed": 0,
  "verdict": "PASS",
  "auto_retrigger_plan_phase": false
}

Verdict Mapping (per schema spec.scoring)

  • 4/4 → PASS (APPROVED)
  • 3/4 → WARNING (APPROVED WITH CONDITIONS)
  • ≤2/4 → BLOCKER (REJECTED) — manual /gsd-plan-phase rerun required (NOT auto-spawn per Phase 2.4 ASSUMPTIONS B-12; v0.3.0 orchestration layer absorbs auto-spawn).

Walker Reference

The walker scripts/run-plan-checker.mjs (T2.2 ship, commit f986d42) implements the canonical scoring algorithm. Agent output JSON MUST match the walker's dimension keys and verdict semantics for CI parity (T2.4 ci.yml step).

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. 5d ago First seen · 46 lines · 48 tokens per session scan A 4c9806bd3abc

Subscribe to this mod's changes

gsd-plan-checker is an agent published in the GitHub repository easyinplay/harnessed (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 48 tokens to every session and 551 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 2026-08-31.