agentleFS
jame-hvjame-hv/brse-toolkit/skills/change-impact/SKILL.md

change-impact

Skill0 starsChanged 5 days agoMITView on GitHub

Use this when a decision, Q&A answer or requirement changes — after a meeting, a client answer or the user's instruction — to trace everything it affects (requirements, approach, estimate lines, Q&A, tests, tasks), show one change proposal for the user to approve, then apply it with new approach/estimate versions and a change log.

8 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

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

    line 14

“Common” is measured: kept by at least 6 in 10 of the 6 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

Before running

<py> below = the Python recorded by /brse-toolkit:setup (runtime.python in ~/.config/brse-toolkit/config.json — read that file directly), else the first of python3, python, py -3 that runs. No Python at all → tell the user to run /brse-toolkit:setup, and continue only with steps that need no script, saying which checks were skipped.

Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

  • error → show it to the user and stop; the config file must be fixed first.
  • workspace_root is null → the folder isn't initialized. Ask once: run /brse-toolkit:init first (recommended — memory and knowledge get saved for next time) or continue once without saving. Running as a subagent dispatched by a main agent → the parent already resolved this; proceed.
  • Otherwise use config.paths (sources, templates, outputs — relative to workspace_root), config.style, config.translation, and the files in .brse/memory/long/. Never assume a folder name the config doesn't list.
  • warnings not empty → mention them in one line (likely a typo in the config).

When to use

A new or superseding D-xxx, an answered Q-xxx, or an R-xxx added / dropped — usually handed over by meeting-intake. Also on "nếu đổi sang phương án X thì ảnh hưởng gì?" (run steps 1–3 only, as a what-if; record nothing).

Steps

  1. Trace: <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py register impact <id> for each changed item. Then search the current approach and estimate files for those IDs (and for the superseded decision's IDs): every estimate row, 前提条件, not-included item and approach section that cites them is affected.
  2. Assess each affected thing — one row each, with the basis:
    • requirement: stays / changes / out of scope
    • approach section: what changes
    • estimate row: old → new effort and why (count × unit, reference, or assumption); technical parts from SE, test effort from QA when they move by more than a few 人日 (ask them with the IDs and the decision)
    • Q&A: now void / needs rewording / new question needed
    • tests, design, open tasks touched
  3. One change proposal, conclusion first:
    D-014 (reuse old module, replaces D-006): estimate −38人日 (412 → 374), approach §3 rewritten,
    Q-011 void, 1 new Q (license of old module), QA test scope −2 screens.
    | # | Item | Now | Proposed | Basis |
    Each row approvable on its own. Stop and wait for the user's yes / edits.
  4. Apply only the approved rows:
    • registers: update R / Q (void: --status void), new Q as draft, new T with owners
    • approach file → new version; estimate via the estimation skill in the project's own template (whatever it is) → new version; both keep a change-log sheet/section: date · version · change · reason (D/Q ids)
    • brse.py register bump approach|estimate --file <path> --reason "…" --decisions D-…
    • new / reworded Q&A → Comtor for wording in the client's language
  5. Check: brse.py register check and cross-check (every in-scope R in the estimate or not-included; same numbers in estimate, approach, Q&A). brse.py register render. Then review-gate before anything goes to the client.

Output

One line: what changed and the new versions (approach v1.3, estimate v1.4: −38人日), then what waits on whom (user / client / which bot). Nothing is sent to the client.

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.