A skill for checking whether a requested code change fits the currently approved specification, the document that defines the work's boundaries.

Use it before implementation, refactoring, or bug fixes that might change scope. It compares the request with specification files and reports whether the work is allowed, needs an extension, or is blocked.

It helps prevent implementation from expanding beyond the agreed requirements or proceeding without a required specification.

scope-check — Skill for Codex by Eliyce

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.

Any agent

npx skills add Eliyce/paqad-ai --skill scope-check

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eliyce/paqad-ai/scope-check/github.svg)](https://agentmods.dev/skills/eliyce/paqad-ai/scope-check)

Your own site

<a href="https://agentmods.dev/skills/eliyce/paqad-ai/scope-check"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/scope-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eliyce/paqad-ai/scope-check"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/scope-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 533 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00533
Opus 5	$0.00007	$0.00267
Sonnet 5	$0.00003	$0.00107
Haiku 4.5	$0.00001	$0.00053

Measured 10d ago against content hash ea812b8fc0ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

scope-check 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check-spec-presence.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/scope-check/SKILL.md · 69 lines

What it actually says

What It Does

Checks whether the requested change is already authorized by the active spec so implementation does not drift into unspecced work.

Use This When

Use this before implementation, refactors, or bug fixes that could quietly expand scope beyond the approved story or solution artifact.

Inputs

Read the request text at request_text.
Read every active spec artifact passed in spec_paths.
Read references/scope-rules.md before deciding whether the request is covered, additive, or out of scope.

Procedure

Run scripts/check-spec-presence.sh — exit 1 means immediately classify as blocked-no-spec and stop.
Extract requested behavior change, modules, and constraints from the request.
Compare against the active spec artifacts only (no inferred memory, no informal context).
Pick a decision from assets/decision-vocabulary.txt (within-scope | extension-needed | blocked-no-spec).
Cite exact spec evidence (file + criterion/passage).
Format per assets/output.template.md; validate with scripts/lint-output.sh.

Output Contract

Match assets/output.template.md: ## Scope Decision (decision token + one-line justification), ## Spec Evidence, ## Required Next Step.
Decision token must come from assets/decision-vocabulary.txt.
Output must pass scripts/lint-output.sh (exit 0).

Escalate / Stop Conditions

Block when no spec artifact exists for feature, bug-fix, refactor, or migration work.
Ask when multiple spec artifacts conflict or define incompatible boundaries.
Do not grant scope based on an unstated workflow or informal memory.

Resources

references/scope-rules.md
scripts/check-spec-presence.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.

10d ago First seen · 69 lines · 14 tokens per session scan A ea812b8fc0ff

Subscribe to this mod's changes

scope-check is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 533 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.

Claude Code Planning agent-framework ai ai-agents cli codex

pr-writing-review

Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…

evalstate/fast-agent · 64 tokens

session-investigator

Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…

evalstate/fast-agent · 68 tokens

auto-go

A command that implements code from a SPEC, a document describing the required behavior and work.

Insajin/autopus-adk · 15 tokens

auto-plan

A code-planning skill that examines a codebase and creates a detailed specification, implementation plan, and acceptance criteria. It can organize requirements using EARS, a structured way to describe how software should behave in different situations.

Insajin/autopus-adk · 25 tokens

agent-pipeline

Multi-agent pipeline orchestration skill.

Insajin/autopus-adk · 10 tokens

adaptive-quality

Per-task execution profile selection based on complexity in Balanced quality mode.