spec-verification

spec-verification is a skill for Claude Code, Codex from tesslio/spec-driven-development-tile. It costs 85 tokens per session (814 once invoked), scanned A, original, MIT.

A checking skill that compares documented requirements, source code, and tests after changes are made. A spec is a written description of how a feature should behave.

In plain words
What is it for?
Use it to validate spec files, check their implementation and test links, run linked tests, and report mismatches.
Why use it?
It finds drift, such as requirements that the code no longer meets, broken links to files or tests, and behavior that was added without documentation.

Skill for Claude CodeCodex

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 skills/tesslio/spec-driven-development-tile/spec-verification
Any agent
npx skills add tesslio/spec-driven-development-tile --skill spec-verification
Clone the repo
git clone --depth 1 https://github.com/tesslio/spec-driven-development-tile

Made for: Claude Code, Codex.

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-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/tesslio/spec-driven-development-tile/spec-verification.svg)](https://agentmods.dev/skills/tesslio/spec-driven-development-tile/spec-verification)
Your own site
<a href="https://agentmods.dev/skills/tesslio/spec-driven-development-tile/spec-verification"><img src="https://agentmods.dev/badge/skills/tesslio/spec-driven-development-tile/spec-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 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 $0.00085 $0.00814
Opus 5 $0.00043 $0.00407
Sonnet 5 $0.00017 $0.00163
Haiku 4.5 $0.00009 $0.00081

Measured 4d ago against content hash f82db5b89277, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-verification 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.

skills/spec-verification/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Verification

Ensure code and tests still reflect the documented requirements. Detect and fix drift between specs, implementation, and tests.

When to use

  • After implementation is complete (before marking work as done)
  • When reviewing PRs that touch spec-covered code
  • When work-review flags potential spec drift
  • Periodically as a maintenance check

Steps

  1. Find all specs. Locate .spec.md files in the project's specs/ directory:

    find specs/ -name "*.spec.md" 2>/dev/null
    
  2. Validate structural integrity. For each spec, check that links resolve:

    • Verify each targets: path exists (expand globs, confirm matches)
    • Verify each [@test] link points to an existing test file
    • Confirm frontmatter has name, description, and at least one target
    # Use the bundled validation scripts:
    ./scripts/validate-specs.sh specs/
    ./scripts/check-spec-links.sh specs/
    

    If either script reports failures, record them as broken-link findings.

  3. Run linked tests. Execute the test files referenced by [@test] links:

    # Extract test paths from specs and run them
    grep -rh '\[@test\]' specs/*.spec.md | sed 's/.*\[@test\] *//' | sed 's/`$//'
    

    If tests fail, diagnose the failure. Determine whether the test, the code, or the spec is wrong before proceeding.

  4. Spot-check targets for drift. Read the files listed in targets: and compare against spec requirements:

    • For each requirement in the spec, confirm the target file implements it
    • Look for logic in target files that contradicts the spec (edge cases, error handling, data contracts)
    • Look for new behavior in target files not mentioned in any spec
  5. Check for drift signals:

    • Behavioral changes in code not mentioned in the spec
    • Newly added tests without matching requirements (or vice versa)
    • Deleted or renamed files that still appear in targets: or [@test] links
    • New code paths in target files that aren't covered by any requirement

Read the full file on GitHub · 87 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. 4d ago First seen · 87 lines · 85 tokens per session scan A f82db5b89277

Subscribe to this mod's changes

spec-verification is a skill published in the GitHub repository tesslio/spec-driven-development-tile (53 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 814 once invoked, about $0.0004 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens