You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
docs(invocation-mode): re-grade disk-hygiene:clean under the 2026-10-18 decision #9706
Part of #6458. Re-grade disk-hygiene:clean under the owner's 2026-10-18 decision on #6458 (D3, option b): a destructive-capable skill becomes model-invocable only if every destructive step provably stops for a person even when it runs unattended. The four class (i) skills are graded one at a time.
Scope
Read plugins/disk-hygiene/skills/clean/SKILL.md, its context/ pages and scripts. For each destructive or mutating step, quote the line that stops it for a person, and say whether that stop holds with no person present (for example a script flag the model can pass, such as --yes, does not hold).
Update its row in docs/conventions/invocation-mode/README.md (the 2026-08-17 grade table) with the evidence and the grade: FLIP to false only when every step holds, otherwise KEEP true citing the step that does not.
On FLIP, set disable-model-invocation: false (or remove the key) in that SKILL.md and add a changelog fragment for the plugin.
Done when
The disk-hygiene:clean row in docs/conventions/invocation-mode/README.md cites the 2026-10-18 decision and quotes each destructive step's stop.
git show HEAD:plugins/disk-hygiene/skills/clean/SKILL.md | grep -c '^disable-model-invocation: true' prints 1 for KEEP or 0 for FLIP, matching the row.
Proposed work class: work-class: scoped
Basis: automated intake triage; the lanes App applied this class.
Size: Small
Complexity: Low
Uncertainty: Knowable
Flags: none
Understood: grade disk-hygiene:clean under the 2026-10-18 decision on #6458 (D3, option b). Read the skill, its context pages and scripts, and quote the line that stops each destructive step for a person. Then update its row in the invocation-mode README as KEEP or FLIP. On FLIP, change the SKILL.md key and add a changelog fragment. The approach is clear from the issue. The grade depends on what the skill's steps do, so someone has to read them first. The issue is a child of #6458. I found no likely duplicates.
The work-resolve-issue run that agent-ready started failed or was cancelled before it reported, or it stopped or the token broker refused it because its workflow files differ from main's. work-unblock removed and added agent-ready back to start a fresh run on main's workflow files. It does this once per version of those files, so if this run fails the same way, a person looks at it.
The work-resolve-issue run that agent-ready started failed or was cancelled before it reported, or it stopped or the token broker refused it because its workflow files differ from main's. work-unblock removed and added agent-ready back to start a fresh run on main's workflow files. It does this once per version of those files, so if this run fails the same way, a person looks at it.
Activity
github-actions commentedon Oct 24, 2026
Proposed work class: work-class: scoped
Basis: automated intake triage; the lanes App applied this class.
Size: Small
Complexity: Low
Uncertainty: Knowable
Flags: none
Understood: grade
disk-hygiene:cleanunder the 2026-10-18 decision on #6458 (D3, option b). Read the skill, its context pages and scripts, and quote the line that stops each destructive step for a person. Then update its row in the invocation-mode README as KEEP or FLIP. On FLIP, change the SKILL.md key and add a changelog fragment. The approach is clear from the issue. The grade depends on what the skill's steps do, so someone has to read them first. The issue is a child of #6458. I found no likely duplicates.Automated triage, applied by the lanes App.
melodic-automation-lanes commentedon Oct 24, 2026
The work-resolve-issue run that
agent-readystarted failed or was cancelled before it reported, or it stopped or the token broker refused it because its workflow files differ from main's. work-unblock removed and addedagent-readyback to start a fresh run on main's workflow files. It does this once per version of those files, so if this run fails the same way, a person looks at it.melodic-automation-lanes commentedon Oct 24, 2026
The work-resolve-issue run that
agent-readystarted failed or was cancelled before it reported, or it stopped or the token broker refused it because its workflow files differ from main's. work-unblock removed and addedagent-readyback to start a fresh run on main's workflow files. It does this once per version of those files, so if this run fails the same way, a person looks at it.