spec-vs-impl-checker

spec-vs-impl-checker is a skill for Claude Code, Codex from Firstp1ck/pi-coding-agent-forge. It costs 48 tokens per session (844 once invoked), scanned A, original, MIT.

A review process that compares a written specification or plan with the code that was built. It traces each requirement to implementation files and tests, then reports missing or mismatched parts.

In plain words
What is it for?
Use it to check functional, validation, security, and interface requirements, and to mark each one as verified, untested, or missing.
Why use it?
It makes gaps between promised behavior and actual behavior easier to find before release or review.

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/firstp1ck/pi-coding-agent-forge/spec-vs-impl-checker
Any agent
npx skills add Firstp1ck/pi-coding-agent-forge --skill spec-vs-impl-checker
Clone the repo
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forge

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-vs-impl-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/spec-vs-impl-checker.svg)](https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/spec-vs-impl-checker)
Your own site
<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/spec-vs-impl-checker"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/spec-vs-impl-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 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 $0.00048 $0.00844
Opus 5 $0.00024 $0.00422
Sonnet 5 $0.00010 $0.00169
Haiku 4.5 $0.00005 $0.00084

Measured 4d ago against content hash ca8a7dfe3a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-vs-impl-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 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.

pi-skill-spec-vs-impl-checker/skills/spec-vs-impl-checker/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-vs-Implementation Checker

Systematically verify that every specification requirement is implemented correctly.

Process

Step 1 — Build Requirement Registry

Extract every requirement from the spec and combined plan into a structured registry:

| Req ID | Source | Section | Requirement | Type |
|---|---|---|---|---|
| REQ-001 | spec.md | 4.1 | Users can register with email/password | Functional |
| REQ-002 | spec.md | 4.1 | Email must be validated (format + uniqueness) | Validation |
| REQ-003 | combined-plan.md | 2 | Passwords hashed with bcrypt (cost 12) | Security |
| REQ-004 | architecture.md | 3.2 | Auth module exposes /api/auth/* endpoints | Interface |

Step 2 — Trace to Implementation

For each requirement, find the implementing code:

| Req ID | Implementation | File(s) | Test(s) | Status |
|---|---|---|---|---|
| REQ-001 | register() handler | src/auth/handlers.rs:45 | test_register | VERIFIED |
| REQ-002 | validate_email() | src/auth/validation.rs:12 | test_email_validation | VERIFIED |
| REQ-003 | hash_password() | src/auth/crypto.rs:8 | — | UNTESTED |
| REQ-004 | router config | src/auth/mod.rs:20 | test_auth_routes | VERIFIED |

Step 3 — Verify Each Requirement

For each traced requirement:

  1. Read the code — Does the implementation match what the spec describes?
  2. Check the tests — Is there a test that verifies this specific requirement?
  3. Run the test — Does the test actually pass?
  4. Check edge cases — Does the implementation handle the edge cases the spec implies?

Status values:

Status Meaning
VERIFIED Implemented correctly, tested, test passes
IMPLEMENTED Code exists but no specific test
UNTESTED Code exists, test exists but doesn't cover this requirement
PARTIAL Partially implemented (e.g., happy path only, missing error handling)
MISSING No implementation found for this requirement
DEVIATED Implementation differs from spec (document how)

Read the full file on GitHub · 107 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 · 107 lines · 48 tokens per session scan A ca8a7dfe3a1c

Subscribe to this mod's changes

spec-vs-impl-checker is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (77 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 844 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.