reversible-agent-task
Run risky or multi-file agent work as a reviewable proposal before mutating the target workspace. Use when a task should produce retained output, inspectable diffs, and an explicit select/apply/discard decision instead of direct edits.
Install
npx skills add https://github.com/markoblogo/abvx-agent-skills/tree/main/skills/reversible-agent-task
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install markoblogo-abvx-agent-skills@llmmart
git clone https://github.com/markoblogo/abvx-agent-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole markoblogo/abvx-agent-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Reversible Agent Task
Use a proposal-first workflow when direct mutation would make review, rollback, or comparison harder.
Use When
- an agent runner, SET bundle, or planning doc mentions retained output, proposal lifecycle, settlement, or reversible traces;
- the task can be attempted in a worktree, draft branch, sandbox, retained-output folder, or external runner proposal;
- multiple possible implementations should be compared before one is applied;
- the target repo should remain unchanged until a human or supervisor reviews the output.
Lifecycle
run: execute the task in a proposal context, such as a worktree, draft branch, sandbox, or retained-output directory.retained_output: keep generated files, diffs, logs, and proof artifacts separate from the target workspace.inspect: review diff scope, verification evidence, assumptions, and expected artifacts.select: mark one retained output as the candidate result.apply: merge or copy the selected proposal into the target workspace only after gates pass.discard: reject the proposal and leave the target workspace unchanged.
Procedure
- Define the target workspace and the proposal workspace.
- State the mutation rule: no direct writes to the target workspace until
apply. - Capture expected artifacts, verification commands, and retained-output path before the run.
- Run the agent or implementation loop in the proposal context.
- Inspect the retained output:
- changed files;
- generated artifacts;
- tests or checks run;
- unresolved assumptions;
- scope drift.
- Choose exactly one settlement action:
select,apply, ordiscard.
Output Shape
Include:
- target workspace;
- proposal workspace or retained-output location;
- lifecycle state reached;
- artifacts produced;
- verification evidence;
- settlement action:
select,apply, ordiscard; - blockers or assumptions.
Guardrails
- Do not present retained output as applied work.
- Do not hide failed proposals; summarize why they were discarded.
- Do not mutate the target workspace during
runorinspect. - Do not use this skill for trivial one-file edits where normal git diff review is enough.
- Keep the proposal mechanism host-agnostic: worktree, branch, sandbox, retained directory, or external runner are all acceptable.
Pair With
pipeline-readiness-gatefor pre/post/ship gate selection.assumption-excavationbefore running high-ambiguity proposals.confidence-fragility-reviewbefore applying a proposal with public or release claims.delivery-baseline-auditbefore calling applied work complete.filesystem-context-disciplinewhen retained outputs, scratchpads, or handoffs need durable file structure.
Provenance
Adapted from proposal lifecycle patterns in reversible agent runtimes such as shepherd-agents/shepherd, narrowed into a host-agnostic ABVX review discipline. This skill does not require Shepherd.
Files (abvx-agent-skills)
-
agents
-
openai.yaml 227 B
Loading…
-
-
SKILL.md 3.3 KB
--- name: reversible-agent-task description: Run risky or multi-file agent work as a reviewable proposal before mutating the target workspace. Use when a task should produce retained output, inspectable diffs, and an explicit select/apply/discard decision instead of direct edits. license: MIT metadata: abvx_status: experimental abvx_origin: adapted abvx_eval_tier: fixture_checked --- # Reversible Agent Task Use a proposal-first workflow when direct mutation would make review, rollback, or comparison harder. ## Use When - an agent runner, SET bundle, or planning doc mentions retained output, proposal lifecycle, settlement, or reversible traces; - the task can be attempted in a worktree, draft branch, sandbox, retained-output folder, or external runner proposal; - multiple possible implementations should be compared before one is applied; - the target repo should remain unchanged until a human or supervisor reviews the output. ## Lifecycle 1. `run`: execute the task in a proposal context, such as a worktree, draft branch, sandbox, or retained-output directory. 2. `retained_output`: keep generated files, diffs, logs, and proof artifacts separate from the target workspace. 3. `inspect`: review diff scope, verification evidence, assumptions, and expected artifacts. 4. `select`: mark one retained output as the candidate result. 5. `apply`: merge or copy the selected proposal into the target workspace only after gates pass. 6. `discard`: reject the proposal and leave the target workspace unchanged. ## Procedure 1. Define the target workspace and the proposal workspace. 2. State the mutation rule: no direct writes to the target workspace until `apply`. 3. Capture expected artifacts, verification commands, and retained-output path before the run. 4. Run the agent or implementation loop in the proposal context. 5. Inspect the retained output: - changed files; - generated artifacts; - tests or checks run; - unresolved assumptions; - scope drift. 6. Choose exactly one settlement action: `select`, `apply`, or `discard`. ## Output Shape Include: - target workspace; - proposal workspace or retained-output location; - lifecycle state reached; - artifacts produced; - verification evidence; - settlement action: `select`, `apply`, or `discard`; - blockers or assumptions. ## Guardrails - Do not present retained output as applied work. - Do not hide failed proposals; summarize why they were discarded. - Do not mutate the target workspace during `run` or `inspect`. - Do not use this skill for trivial one-file edits where normal git diff review is enough. - Keep the proposal mechanism host-agnostic: worktree, branch, sandbox, retained directory, or external runner are all acceptable. ## Pair With - `pipeline-readiness-gate` for pre/post/ship gate selection. - `assumption-excavation` before running high-ambiguity proposals. - `confidence-fragility-review` before applying a proposal with public or release claims. - `delivery-baseline-audit` before calling applied work complete. - `filesystem-context-discipline` when retained outputs, scratchpads, or handoffs need durable file structure. ## Provenance Adapted from proposal lifecycle patterns in reversible agent runtimes such as `shepherd-agents/shepherd`, narrowed into a host-agnostic ABVX review discipline. This skill does not require Shepherd. -
SKILL_CARD.md 1.5 KB
Loading…
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.