{"slug":"corroborate-by-independent-reruns","title":"corroborate-by-independent-reruns","summary":"Use when a candidate patch or answer needs independent corroboration before it is trusted. Not for multi-stance investigation: use council.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-30T19:50:09.020223Z","repo":{"url":"https://github.com/OutlineDriven/outline-driven-development","stars":54,"forks":10,"license":"Apache-2.0","updatedAt":"2026-09-28T03:16:21Z"},"bodyHtml":"
\n

name: corroborate-by-independent-reruns\ndescription: 'Use when a candidate patch or answer needs independent corroboration before it is trusted. Not for multi-stance investigation: use council.'\ndisable-model-invocation: true

\n

Corroborate by independent reruns

\n

Contract

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
FieldBound contract
TriggerA candidate patch or answer needs independent corroboration before it is trusted
AuthorityReversible local: writes only the named corroboration report; rollback is discarding it if rejected. No remote mutation. Each run mutates only its own isolated sandbox, discarded after capture.
Side effectRuns N isolated sandboxed attempts and returns the majority patch plus its agreement count; byte identity is a corroboration signal, not a correctness oracle; no-change runs never carry consensus
DoneEither a strict majority of launched runs produced byte-identical output and it is returned with its count, or no consensus is reported
\n

Inputs

\n\n

Procedure

\n
    \n
  1. Receive the candidate, N, and the sandbox execution command. Bound scope to N isolated runs; do not widen to additional runs or mutate the shared working tree. Done when: scope is bounded to exactly N isolated runs with no shared-tree mutation.
    2. \n
  2. Launch N isolated sandboxed attempts, each starting from the same clean baseline and running the same task without access to any other run's output. Done when: N isolated runs are launched, each from a clean baseline with no cross-run access.
    3. \n
  3. Capture each run's full output bytes. Done when: every launched run's full output bytes are captured.
    4. \n
  4. Classify each output: a no-change run whose output is byte-identical to the baseline or empty is excluded from consensus and never carries consensus. Done when: every output is classified as candidate or no-change, with no-change runs excluded from consensus.
    5. \n
  5. Group the remaining outputs by byte identity. If a single byte-identical group is a strict majority of the N launched runs (count > N/2), return that output with its agreement count. Done when: outputs are grouped by byte identity and either a strict-majority group is identified or no majority exists.
    6. \n
  6. If no byte-identical group reaches a strict majority, report no consensus. Done when: no-consensus is reported with the per-run output groups, or the strict-majority output is returned with its count.
    7. \n
  7. Treat byte identity as a corroboration signal only, never as a correctness oracle; do not assert the majority output is correct. Done when: the result is presented as a corroboration signal with no correctness claim.
    8. \n
\n

Failure and recovery

\n\n

Output

\n

Either the strict-majority byte-identical patch or answer with its agreement count, or a no-consensus classification listing the per-run output groups. Never a correctness claim.

\n","files":[{"path":"agents/openai.yaml","sizeBytes":220,"isText":true},{"path":"SKILL.md","sizeBytes":3803,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-30T19:52:30.09496Z","sha256":"FAB2430EEF074109FF01E6ECF52A0EEAB772FD37BA7EA0649DE21CF29445AC76","sizeBytes":1798},"review":null,"source":{"repositoryUrl":"https://github.com/OutlineDriven/outline-driven-development","path":".devin/skills/corroborate-by-independent-reruns","license":"Apache-2.0","commit":"b0e8ce89a19fac880251dc3ea1babfeb4503a4fe","subtreeSha":"A23DA497B94D9018B2BBE0FBF932EF47BC7B943277684FEF8B910FD4E5632138","lastSyncedAt":"2026-09-30T19:49:48.917811Z"},"reviewedAt":"2026-09-30T19:57:17.564533Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/OutlineDriven/outline-driven-development/tree/main/.devin/skills/corroborate-by-independent-reruns"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install outlinedriven-outline-driven-development@llmmart"},{"target":"git","command":"git clone https://github.com/OutlineDriven/outline-driven-development.git"}]}