gate-attribution · zaxbyhub — Claude Code skill: what it does, how to install
gate-attribution assigns reviewer and test engineer verdicts to individual plan tasks during swarm batch runs. Activates when dispatches return multi-task rows.
MIT ★ 539 updated 2026-10-29
npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a claude-codeWhat gate-attribution does
This skill defines the attribution protocol for delegation-gate runtimes. Single-task runs link results through taskId, whereas set-dispatches require strict row outputs such as [REVIEWED] | task-X.Y | APPROVED or [TESTED] | X.Y | PASS.
Every parsed row writes a distinct evidence record to .swarm/evidence/{taskId}.json. A single multi-task summary file fails the verification gate because prose text cannot satisfy individual task requirements.
This workflow applies only in environments with swarm controller dispatch tools available in the active session.
What it helps with
- Map batch review and test outputs to specific task identifiers
- Write isolated evidence entries to
.swarm/evidence/{taskId}.json - Structure multi-task test passes via
dispatch_lanes_async
Example prompts for the agent
- Verify task 2.1, execute the test suite, and output a [TESTED] verdict line
- Set up parallel verification via dispatch_lanes_async with one lane per taskId
- Format review feedback for tasks 1.1 and 1.2 using [REVIEWED] | task-id | verdict rows
How to install gate-attribution
1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a claude-code2Manually: put the files in place
~/.claude/skills/gate-attribution/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gate-attribution/
1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a codex2Manually: put the files in place
.agents/skills/gate-attribution/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a cursor2Manually: put the files in place
.cursor/skills/gate-attribution/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ZaxbyHub/opencode-swarm .opencode/skills/gate-attribution2Manually: put the files in place
.github/skills/gate-attribution/SKILL.md1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a gemini-cli2Platform CLI
gemini skills install https://github.com/ZaxbyHub/opencode-swarm --path .opencode/skills/gate-attributionManually: put the files in place
.devin/skills/gate-attribution/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gate-attribution
How to install gate-attribution in Claude Code?
Run npx skills add ZaxbyHub/opencode-swarm --skill gate-attribution -a claude-code.
What does gate-attribution do?
It parses structured [REVIEWED] and [TESTED] lines into task-scoped evidence files required to satisfy gate checks.
Why does prose verification fail the gate?
Batched runs without explicit parseable rows are treated as ambiguous, so the tracker fails closed to prevent incorrect task completions.
Source text
SKILL.md · MIT
---
name: gate-attribution
description: Per-task gate dispatch protocol for reviewer/test_engineer set-dispatch attribution. Activates when dispatch_lanes returns set-dispatch verdict rows that must be attributed to plan tasks. Documents single-task attribution plus parseable set-dispatch reviewer/test_engineer rows.
metadata:
audience: swarm-plugin
---
# Gate Attribution
## The rule
The gate tracker attributes reviewer/test_engineer dispatches PER TASK. A
single-task prompt still attributes by `task_id` / `taskId` / unambiguous prompt
task ID. A set-dispatch can also count per-task when the reviewer/test_engineer
output includes parseable per-task rows:
```
[REVIEWED] | task-2.1 | APPROVED | ...
[TESTED] | 2.1 | PASS | ...
```
`[REVIEWED]` verdicts are `APPROVED | REJECTED | CONCERNS`; `[TESTED]` verdicts
are `PASS | FAIL | SKIPPED`. Rows with `task-X.Y` are normalized to `X.Y`;
unsafe or non-plan IDs are ignored.
Each parseable per-task verdict row creates gate evidence (regardless of verdict
value); the gate's pass/fail decision is made elsewhere from the accumulated
evidence. If no rows are parseable, attribution falls back to the single-task
rule.
## Protocol
1. **For unrelated or high-risk tasks:** Dispatch separate reviewer and/or test_engineer lanes with exactly ONE taskId.
2. **For a true set-dispatch:** Require one `[REVIEWED] | task-id | verdict | ...` (or `[TESTED] | ...`) row per task in the returned output. Each parseable row creates gate evidence; the gate decision is made from the accumulated evidence.
3. **Minimize overhead via parallel dispatch when set-dispatch is not appropriate:**
```
dispatch_lanes_async with:
- common_prompt: shared verification context
- lanes: one lane per task, each with a single taskId
- max_concurrent: up to 3
```
This protocol applies only in sessions whose actual tool list includes the
swarm controller's dispatch tools; on hosts without the controller it is not
applicable — do not fabricate set-dispatch rows.
4. **Collect + attribute:** Single-task lanes auto-attribute to their taskId; set-dispatch rows auto-attribute per parsed row.
5. **Do NOT rely on prose summaries:** A batched dispatch without parseable rows is ambiguous and does not count per-task.
Gate evidence is persisted independently as `.swarm/evidence/{taskId}.json` for each task. Each parseable set-dispatch row causes the hook to write one task-scoped evidence file for that task (regardless of verdict value); a single multi-task evidence file cannot satisfy any task.
## Optimization for trivial tasks
For pure ceremony gates (1-line doc fix):
```
TASK: Verify task X.Y. Run skill-mirrors.test.ts. PASS/FAIL.
taskId: X.Y
```
## Why this exists
The gate tracker (the delegation-gate runtime) keys delegation chains by
`sessionID`. Ambiguous multi-task prompts still fail closed, but parseable
`[REVIEWED] | task-id | ...` rows provide explicit per-task attribution for
set-dispatches. Tracked in issue #1746 item 6.
© ZaxbyHub · MIT · ZaxbyHub/opencode-swarm
Similar skills
All skills for Agent setup: memory, context, orchestration →gate-attribution by other authors comes first.