A set of checks that keeps an implementation limited to the requested work. Scope creep means adding unrelated changes while working on a task.

Use it when starting implementation, considering a related fix, or feeling tempted to change code outside the original request.

It helps prevent unnecessary refactoring, cleanup, documentation edits, or performance work from expanding the task and its risk.

scope-guard — Skill for Claude Code and Codex by strikersam

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 strikersam/autonomous-ai-agency --skill scope-guard

Clone the repo

git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/scope-guard/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/scope-guard)

Your own site

<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/scope-guard"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/scope-guard/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/strikersam/autonomous-ai-agency/scope-guard"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/scope-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 803 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00000	$0.00803
Opus 5	$0.00000	$0.00402
Sonnet 5	$0.00000	$0.00161
Haiku 4.5	$0.00000	$0.00080

Measured 12d ago against content hash c490b9989fe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

scope-guard 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 12d 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.

.agents/skills/scope-guard/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: scope-guard

Purpose

Detect and prevent scope creep during implementation. Keeps Claude focused on the original task and flags when it's about to do more than asked.

Trigger

Use:

At the start of any implementation task (define scope)
During implementation when you notice you're about to change something unrelated
When a fix "requires" refactoring something else
When you feel the urge to "clean up while you're in here"

Process

Step 1: Define the Scope Contract

At task start, write an explicit scope contract:

## Scope Contract

### In Scope
- [specific change 1]
- [specific change 2]

### Out of Scope (explicitly)
- Refactoring existing working code
- Improving unrelated tests
- Updating unrelated documentation
- Performance improvements not requested
- Style changes in files not being touched

### Allowed Side Effects
- Fixing a bug directly caused by the change
- Updating tests for code being modified
- Updating docs directly describing the feature being added

Step 2: Pre-Implementation Check

Before touching any file, ask:

Is this file directly related to the requested change?
Would the change work without modifying this file?
Is this a "nice to have" or a "need to have"?

If the answer to #2 is "yes" or #3 is "nice to have" — do NOT touch the file.

Step 3: During Implementation — The Scope Test

When you notice any of these urges, apply the scope test:

Red Flags (stop and evaluate):

"While I'm here, I should also..."
"This would be cleaner if I refactored..."
"I noticed this other bug..."
"The tests could be improved..."
"This naming is inconsistent across the codebase..."

The Scope Test:

Was this mentioned in the original task? → If no, stop.
Does the original task FAIL without this change? → If no, stop.
Is this a security or data-integrity issue? → If yes, flag it separately.

Step 4: Parking Lot

When you catch scope creep, don't ignore it — park it:

## Parking Lot (Out of Scope - Future Issues)
- [ ] `src/utils.py` line 45: inconsistent error handling pattern — could be standardized
- [ ] `tests/test_api.py`: test coverage gaps in edge cases
- [ ] Performance: N+1 query detected in unrelated endpoint

Read the full file on GitHub · 96 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.

12d ago First seen · 96 lines · 0 tokens per session scan A c490b9989fe0

Subscribe to this mod's changes

scope-guard is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 803 tokens. 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.

Project management agentic-ai ai-agents ai-automation ai-infrastructure ollama openai-compatible

gsd-tools

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

a5c-ai/babysitter · 62 tokens

scope-guard