spec-evaluator

spec-evaluator is a skill for Claude Code from nguyenvanphituoc/shapeup-sdlc-plugin. It costs 117 tokens per session (3,587 once invoked), scanned A, original, MIT.

A skeptical evaluation skill for checking a completed task against its written specification and acceptance criteria. It exercises the running application and returns a pass-or-fail result with evidence and file-and-line bug details.

In plain words
What is it for?
Use it to evaluate, QA, or verify an implemented task, repeat checks after fixes, and provide structured results for a planner-and-builder workflow.
Why use it?
It prevents approval based on claims or assumptions: every criterion needs collected evidence, and missing evidence is treated as a failure.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the shapeup-sdlc-plugin plugin — 17 skills, 11 commands, 4 hooks shipped together

Good fit Use it to evaluate, QA, or verify an implemented task, repeat checks after fixes, and provide structured results for a planner-and-builder workflow.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add nguyenvanphituoc/shapeup-sdlc-plugin
Claude Code
/plugin install shapeup-sdlc-plugin

Made for: Claude Code.

Or install shapeup-sdlc-plugin, the plugin that ships this one along with the rest of its 17 skills, 11 commands, 4 hooks.

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 spec-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator.svg)](https://agentmods.dev/skills/nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator)
Your own site
<a href="https://agentmods.dev/skills/nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator"><img src="https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00117 $0.03587
Opus 5 $0.00059 $0.01793
Sonnet 5 $0.00023 $0.00717
Haiku 4.5 $0.00012 $0.00359

Measured 7d ago against content hash 4527278a14e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

spec-evaluator 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 7d 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.

skills/spec-evaluator/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Evaluator (the single judge, pure worker v1.0)

Assume broken until proven working. Grade evidence, not claims. Return data, not writes.

The judge in a planner → generator → evaluator loop. It reads the committed spec, exercises the running app, and returns a hard-threshold verdict plus a file:line bug list — as a WorkResult envelope the orchestrator ingests. The generator fixes; the evaluator re-runs.

Core guarantee — skeptical by default. Out-of-the-box an LLM is a lenient QA: it finds a real defect, then talks itself into approving anyway. This skill inverts that posture. A criterion with no collected evidence is a FAIL, never a pass-by-assumption.

Anti-leniency protocolreferences/anti-leniency.md — read before printing any verdict. Verdict ledger (re-probe + confidence + flip detection)references/verdict-ledger.md. Dimension contract (injection interface)references/dimension-contract.md. Where any reference file describes writing shared state (task files, .verdicts ledger, run-state), the pure-worker contract overrides it: that data returns in the WorkResult and the orchestrator's ingest script performs the write. Old gate names in reference files map 1:1 onto the core process below: GATE V0/V0.5 = input contract + dimension resolution, GATE V1 = CONTRACT, Phase A = PROBE, GATE V2 = VERDICT, Phase B = REPORT; GATE V3 (sign-off) is retired — pausing is the caller's interaction policy.


Input contract — the WorkOrder

Invoked as --order <path>. Fields you may rely on (absent = unknown, never inferred):

Field What it is
payload.spec_folder The committed grading truth: usecases/ + domain-model.md (+ contracts/, scope-summary.md, _index.md). No usecases/ → HARD STOP, nothing to grade against
payload.feature Feature slug — scopes the probe and names the report
payload.dimensions[] The active dimension set (the caller resolved precedence). Absent → [spec-conformance] + the auto-enable rules below
payload.run_cmd How to start the running app. Absent standalone → ask; absent orchestrated → ESCALATE, do not guess
payload.t0_artifacts[] Per-scope T0 verdict paths for this round (scoped specs). An artifact listed but missing/red on disk, or a scoped spec with none listed → the round is NOT gradeable: return status: failed naming the scope — a structural precondition, not a criterion
payload.browser cli (default, ~4x cheaper) | mcp | none
payload.tasks[] Traceability only (which UCs a task claims): NEVER a grading source — the committed UC text is the criterion, a paraphrase mismatch is a finding
substrate.allowed Your only write surface: .shapeup/<slug>/evaluation/** (the report + evidence)

Read the full file on GitHub · 231 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. 7d ago First seen · 231 lines · 117 tokens per session scan A 4527278a14e7

Subscribe to this mod's changes

spec-evaluator is a skill published in the GitHub repository nguyenvanphituoc/shapeup-sdlc-plugin (2 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 3,587 once invoked, about $0.0006 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.