spec-diff

spec-diff is a skill for Codex from Eliyce/paqad-ai. It costs 18 tokens per session (522 once invoked), scanned A, original, MIT.

A comparison step that checks a new request against the current specification and classifies it as already covered, an extension, or a conflict.

In plain words
What is it for?
Use it when new feature requests, constraints, or behavior changes arrive for an existing story or solution.
Why use it?
It prevents work from quietly changing approved behavior and shows which requirement supports the decision.

Skill for Codex

Written for Codex: agents/openai.yaml present.

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/eliyce/paqad-ai/spec-diff
Any agent
npx skills add Eliyce/paqad-ai --skill spec-diff
Clone the repo
git clone --depth 1 https://github.com/Eliyce/paqad-ai

Made for: 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-diff

README.md
[![agentmods](https://agentmods.dev/badge/skills/eliyce/paqad-ai/spec-diff.svg)](https://agentmods.dev/skills/eliyce/paqad-ai/spec-diff)
Your own site
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/spec-diff"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/spec-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 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 $0.00018 $0.00522
Opus 5 $0.00009 $0.00261
Sonnet 5 $0.00004 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 6d ago against content hash b3391d8379b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-diff 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract-ac-ids.sh, scripts/lint-output.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

runtime/base/skills/spec-diff/SKILL.md · 68 lines

What it actually says

What It Does

Compares an incoming request against the active spec so the framework can tell whether the work is already covered, extends the spec, or conflicts with it.

Use This When

Use this when new work arrives against an existing story or solution and you need to decide whether to continue, extend the spec, or stop because the request conflicts with approved behavior.

Inputs

  • Read the incoming request text from request_text.
  • Read the active spec artifacts from spec_paths.
  • Read references/spec-diff-rules.md before classifying the request.

Procedure

  1. Run scripts/extract-ac-ids.sh <spec-paths...> to load the canonical AC id set.
  2. Extract behavior, constraints, and affected modules from the new request.
  3. Compare against the active specs only; pick a decision token from assets/decision-vocabulary.txt.
  4. Cite the exact AC id / passage that supports the call (or note that no AC matches).
  5. Format per assets/output.template.md; validate with scripts/lint-output.sh.

Output Contract

  • Match assets/output.template.md: ## Spec Diff Decision (decision token + justification), ## Evidence, ## Implication.
  • Decision token must be covered | extension | conflict.
  • Output must pass scripts/lint-output.sh (exit 0).

Escalate / Stop Conditions

  • Ask when the active spec set is incomplete or internally contradictory.
  • Warn when the request implies a behavioral conflict with the accepted solution.
  • Do not silently respec work that is already covered by the current artifacts.

Resources

  • references/spec-diff-rules.md
  • scripts/extract-ac-ids.sh
  • scripts/lint-output.sh
  • assets/output.template.md
  • assets/decision-vocabulary.txt
  • .paqad/
  • agents/openai.yaml
Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 68 lines · 18 tokens per session scan A b3391d8379b9

Subscribe to this mod's changes

spec-diff is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 522 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

HKUDS/nanobot · 22 tokens

summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

HKUDS/nanobot · 32 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens