Use a visible, bounded workflow for non-trivial changes so the result remains reviewable and safer.
Trigger boundary
Use this skill when:
the change affects code, config, docs, or operational surfaces in a meaningful way
the task benefits from an explicit plan and verification path
the task touches more than a trivial wording fix
Do not use this skill when:
the edit is tiny and has no meaningful review or operational consequence
a more specific risk skill should be used instead
Inputs
target goal
touched files or surfaces
main risk
intended validation path
rollback idea
Outputs
explicit plan
scoped change
named verification result
concise final report
Procedure
state the goal and touched surfaces
identify the main risk and think about rollback before editing
prepare the smallest reviewable change
avoid unrelated cleanup or opportunistic refactors
apply the change inside the declared scope
run or name explicit verification
report what changed, what was verified, and what remains risky
Contracts
the change must remain reviewable
verification must be explicit, not implied
the change should stay inside the declared scope
rollback thinking should exist before apply
Risks and anti-patterns
over-formalizing trivial edits
symbolic verification that creates false safety
using the report as a substitute for a readable diff
silently expanding the task during implementation
Verification
confirm a plan existed before apply
confirm the change stayed scoped
confirm at least one explicit verification step was run or intentionally skipped with explanation
confirm the report includes outcome and rollback thinking
Technique traceability
Manifest-backed techniques:
AOA-T-0001 from 8Dionysus/aoa-techniques at ea49abf4f7e96506feed56eb87a9052cbe4408a5 using path techniques/agent-workflows/plan-diff-apply-verify-report/TECHNIQUE.md and sections: Intent, When to use, Inputs, Outputs, Core procedure, Contracts, Risks, Validation
AOA-T-0002 from 8Dionysus/aoa-techniques at ea49abf4f7e96506feed56eb87a9052cbe4408a5 using path techniques/docs/source-of-truth-layout/TECHNIQUE.md and sections: summary
Adaptation points
Project overlays should add:
local source-of-truth files
local validation commands
local risk tiers
approval or review rules
1---2name: aoa-change-protocol3description: aoa-change-protocol4---56# aoa-change-protocol78## Intent910Use a visible, bounded workflow for non-trivial changes so the result remains reviewable and safer.1112## Trigger boundary1314Use this skill when:15- the change affects code, config, docs, or operational surfaces in a meaningful way16- the task benefits from an explicit plan and verification path17- the task touches more than a trivial wording fix1819Do not use this skill when:20- the edit is tiny and has no meaningful review or operational consequence21- a more specific risk skill should be used instead2223## Inputs2425- target goal26- touched files or surfaces27- main risk28- intended validation path29- rollback idea3031## Outputs3233- explicit plan34- scoped change35- named verification result36- concise final report3738## Procedure39401. state the goal and touched surfaces412. identify the main risk and think about rollback before editing423. prepare the smallest reviewable change434. avoid unrelated cleanup or opportunistic refactors445. apply the change inside the declared scope456. run or name explicit verification467. report what changed, what was verified, and what remains risky4748## Contracts4950- the change must remain reviewable51- verification must be explicit, not implied52- the change should stay inside the declared scope53- rollback thinking should exist before apply5455## Risks and anti-patterns5657- over-formalizing trivial edits58- symbolic verification that creates false safety59- using the report as a substitute for a readable diff60- silently expanding the task during implementation6162## Verification6364- confirm a plan existed before apply65- confirm the change stayed scoped66- confirm at least one explicit verification step was run or intentionally skipped with explanation67- confirm the report includes outcome and rollback thinking6869## Technique traceability7071Manifest-backed techniques:72- AOA-T-0001 from `8Dionysus/aoa-techniques` at `ea49abf4f7e96506feed56eb87a9052cbe4408a5` using path `techniques/agent-workflows/plan-diff-apply-verify-report/TECHNIQUE.md` and sections: Intent, When to use, Inputs, Outputs, Core procedure, Contracts, Risks, Validation73- AOA-T-0002 from `8Dionysus/aoa-techniques` at `ea49abf4f7e96506feed56eb87a9052cbe4408a5` using path `techniques/docs/source-of-truth-layout/TECHNIQUE.md` and sections: summary7475## Adaptation points7677Project overlays should add:78- local source-of-truth files79- local validation commands80- local risk tiers81- approval or review rules
Run npx skillmds@latest add majiayu000/aoa-change-protocol in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
aoa-change-protocol It is listed under Productivity on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.