boshu2/agentops/premortem

Premortem

Premortem is an optional plan-challenge strategy. It asks one fresh context to identify concrete ways the resolved bead or caller intent could fail before implementation. It is not part of the required RPI sequence and does not authorize readiness. Plan's shared challenge method owns optional exchange, dispatch and stopping rules; when no fresh context can be started, step 2's labelled self-judged fallback replaces its no-stand-in rule here. Premortem owns the three checks below. Neighbours: general advice is Review, acceptance of a finished change is Validate, and several independent views are Council.

Run the checks in this order and report findings in the same order: a finding from the first or second check outranks any single technical risk the third check constructs.

The first check: who verifies, and are they fresh?

Test the plan's evidence shape before any technical risk: for every unit of work, who verifies it, and is the verifying context distinct from the one that authored it? CI and existing deterministic checks the author did not write count as distinct verifiers, and for an ordinary unit they are enough (Validate). Two shapes are findings: a unit graded only by checks its author wrote, as in a closure step "the implementer runs its own tests and closes"; and a unit Validate lists as costly with no fresh author-distinct read. Report each shape once, listing its units. Self-graded green is the classic false-done, and it ranks first because it silently converts every other failure into a shipped one.

The second check: which steps are one-way doors?

Walk the steps and mark each two-way (the plan can back out of it) or one-way (it cannot). For every one-way step name the exact undo cost, the point of no return, and who holds the handle when it is crossed: the caller, or an agent deciding inside a batch. A two-way failure costs a retry; a one-way failure costs the thing itself. Watch for nineteen reversible steps followed by an irreversible one, where the reflex trained by the first nineteen answers the twentieth.

The named failure mode is reversibility asserted, not traced: a rollback section that says "fully reversible" while one step revokes a credential, force-pushes or publishes. A material irreversible action outside existing caller authority is a finding; Plan's Who decides owns undo cost and authorization, and prior authorization stays valid, so do not demand repeated approval at the crossing or call every uncertain detail irreversible. Stop condition: every step carries a mark, and every one-way mark carries its undo cost.

The third check: construct the failure

Draw candidate failures from what the plan takes for granted, not from a generic risk list. Typical premises: a tool or service behaving as the plan describes, the work holding at volumes far above or below what it expects where volume matters, steps finishing in the stated order and time, and acceptance, edge behavior, scope and dependencies being complete. Aim first at the decision other steps rest on, and at any one-way step whose deciding premise is inferred rather than cited. Name the fact that would show each premise false; when it can be looked up now, look it up instead of reporting the premise as a risk.

For every candidate failure, attempt a concrete defeat: write the input, command sequence or repository state that would make the plan fail, and run or cite the check that shows whether the plan survives it. When execution is not available, the constructed input or sequence plus a cited fact (file and line, documented behavior, an observed output) counts as the attempt. A failure you could not construct is reported as attempted-and-blocked with the obstacle named, which is itself evidence for the plan. The named failure mode is armchair pessimism: imagined risks with no construction, which reads as diligence while testing nothing. A finding with neither a construction nor a blocking fact is deleted, not softened.

Workflow

1. Resolve the existing intent source and inspect its acceptance, non-goals,

evidence requirements and declared write scope.

1. Judge from a context that did not write the plan, following the shared

challenge method for identity, model selection, authorization and bounds. A plan the caller wrote can be judged here, with the caller as author. If this context wrote the plan and no fresh context can be started, run the checks anyway, state that the independence leg is missing, and return inline findings; never describe them as independent.

1. Run the three checks against cited repository facts. For integration or

extension plans where anchoring on the working design is the risk, add the derivation-diff challenge.

1. Return one complete, bounded set of concrete findings with checked and

not-checked scope, then stop: the caller decides whether to revise the plan or invoke RPI.

It's working if

Observable in the output:

• each unit names its verifier, and each self-verification shape is one

finding listing its units;

• each step is marked, and each one-way mark names its undo cost and point of

no return;

• each finding cites a defeat attempt or the fact that blocked it;
• the set is bounded: a review that flags every step has reported nothing.

Boundary

Emit advisory findings, no verdict of any version, readiness, admission or permission. Do not implement, validate the candidate, retry, repair, schedule, claim, change acceptance, operate Git, close work, release or deliver. Council or Idea Genie duel mode may be caller-supplied evidence, but Premortem requires neither and cannot turn consensus into approval. Any plan edit creates a new subject for a later caller-initiated Premortem.

Output

Return findings inline by default:

Findings (in check order, then most consequential first within each check)
1. <step> - <how it fails> - <construction, or the fact that blocked it> - <consequence>
Verifiers: <unit>: <who verifies>
Steps: <step>: two-way | one-way - <undo cost> - <point of no return> - <who holds the handle>
Checked: <what was examined>. Not checked: <what was not>.
Independence: <judge context, distinct from author> or "missing: <reason>"

<skill-dir> is the directory that contains this SKILL.md. Claude Code shows it as "Base directory for this skill"; Codex lists this skill's SKILL.md path; in an AgentOps source checkout it is skills/premortem. Replace <skill-dir> with that absolute path before running a command. The working directory stays the user's repository. If the host did not show where this skill is installed, use the directory of the SKILL.md you read. If you cannot determine it, do not guess a path or run a same-named script from the current repository; say the bundled script is unavailable and check the review's fields by hand against its schema.

When the caller requests a durable review, return premortem-plan-review.v1 and check it with bash "<skill-dir>/scripts/validate-output.sh" <review.json>. Its intent_digest is the 64-hex SHA-256 of the exact intent text as supplied: shasum -a 256 plan.md | cut -d' ' -f1 for a file, or printf '%s' "$TEXT" | shasum -a 256 | cut -d' ' -f1 for pasted text. author_context_id names who wrote the plan (the caller, or that session's ID) and judge_context_id names this context. The form has no fields for verifiers or step marks, so it is lossy: record each inline Verifiers: and Steps: line verbatim in checked, and put each finding's construction or blocking fact in its evidence. The validator rejects identical author and judge IDs but checks only that the strings differ, not that an independent judge ran, so a review without one stays inline. An empty finding set means only that this optional challenge found no concrete defect; it is never a lifecycle gate.