agentleFS
CalebAnderson-CoderCalebAnderson-Coder/ai-agency-os-starter/skills/clients/scope-guard/SKILL.md

scope-guard

Skill0 starsChanged 21 days agoMITView on GitHub

Check any client request against the contracted scope, flag out-of-scope work, and draft a polite change order with price and timeline. Use whenever a client asks for something new, "quick", "small", "extra", or "while you're at it".

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If SCOPE.md is missing or empty, stop and ask for the SOW.

    line 15
  2. Very specific:

    Read SCOPE.md and CHANGES.md.

    line 18
  3. Distinctive:

    Never say "no". Always give a path to yes (paid or swap).

    line 46
  4. Distinctive:

    Never invent a rate — use SCOPE.md.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Scope Guard

Stops unpaid scope creep without damaging the client relationship. Drafts only — never sends anything.

Inputs

  • clients/<slug>/SCOPE.md — contracted deliverables, monthly quantities, revisions, "Not included" list, hourly rate.
  • clients/<slug>/CHANGES.md — previous requests this month.
  • The client's request (pasted email, Slack message or call note).

If SCOPE.md is missing or empty, stop and ask for the SOW. Do not guess the scope.

Procedure

  1. Read SCOPE.md and CHANGES.md. Count what was already delivered or approved this month.
  2. Split the request into individual asks (one client message often hides 2–3 asks).
  3. Classify each ask:
    • IN SCOPE — cite the exact SCOPE.md row.
    • OVER QUANTITY — in scope but above the monthly quantity (e.g. 5th post of 4).
    • OUT OF SCOPE — not in SCOPE.md, or listed under "Not included".
    • UNCLEAR — write ONE clarifying question; do not quote yet.
  4. For over/out-of-scope asks: estimate hours (state assumptions), price = hours × rate from SCOPE.md (round up to the nearest 0.5 h), earliest delivery date that does not push contracted deadlines.
  5. Draft the reply in the client's voice (brand/voice.md if it exists). Offer two options: paid add-on, or swap for an in-scope item this month.
  6. Append one row per ask to CHANGES.md: date, request, class, quote, status (quoted / approved / declined / swapped / free-goodwill).

Output format

## Scope check — <client> — <date>
| Ask | Class | Evidence | Hours | Quote |
|---|---|---|---|---|

### Draft reply (not sent)
<reply>

### CHANGES.md rows added
<rows>

Draft reply pattern

Happy to help with this. [In-scope part] is already covered and will ship by [date]. [Extra part] is outside our current plan (we have [X] included) — it's about [hours] h, so [price], delivered by [date]. Want me to add it? Or we can swap it for [in-scope item] this month at no extra cost.

Rules

  • Never say "no". Always give a path to yes (paid or swap).
  • Never invent a rate — use SCOPE.md. If none is defined, ask.
  • Goodwill freebies are allowed but must be logged as free-goodwill with hours.

Monthly

Summarize CHANGES.md: approved extras billed, goodwill hours given, swaps. If goodwill hours > 10% of contracted hours, recommend a scope or price change at renewal.

Example

See examples/acme-plumbing/ in the repo: a real SCOPE.md, a client request, and the expected output.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.