Use when Codex is running work that originated from DecisionsAI tickets, projects, workflows, or Initiative proposals.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Treat the supplied Decisions project, ticket, workflow, callback, and prior-step packet as authoritative. Work in the named project and do not create another ticket, plan, workflow, or branch unless explicitly requested. Prefer the Codex IDE/chat surface as the primary execution context. The CLI is fallback transport for automation or setup checks.
This chat is the Codex IDE thread for the open project. It is independent of the Decisions Development section and whichever harness that section is using. A follow-up from the user stays in this chat. The reporter prints thread_id= and locks that Codex thread for the project. Pass --thread-id with that value on later reports in this chat. Pass --new-thread only when the user asked to start a new Codex thread.
decisions-harness-stack as the capability index. Skills including Impeccable, Playwright, computer-use, Ponytail, Fallow, content, research, and SaaS routing remain available on demand.For any normal Codex IDE/chat prompt inside a DecisionsAI project folder, report the turn through the quiet project IDE session reporter. At the start:
python3 ~/plugins/decisions-codex/scripts/report_decisions_event.py --event-type codex_prompt_submitted --status observed --input "<user prompt>" --thread-id "<thread id when known>"
Before the final response:
python3 ~/plugins/decisions-codex/scripts/report_decisions_event.py --event-type codex_completed --status completed --output "<short result summary>" --thread-id "<thread id when known>"
If both sides are only available at the end, use --turn-input and --turn-output. The reporter exits quietly when DecisionsAI is unavailable.
When a [DECISIONS CODEX CALLBACK] block is present, report meaningful lifecycle events: codex_started, codex_prompt_submitted, user_steer, codex_progress, codex_waiting, codex_needs_input, codex_interrupted, codex_completed, and codex_failed. Report human steering instead of keeping it only in Codex. Do not emit routine tool chatter as progress.
Return concise, checkpoint-friendly results:
Status: completed | failed | needs_input
Summary: ...
Files changed: ...
Tests: ...
Evidence: ...
Blockers: ...
Next step: ...
Include artifact paths needed by the next step. If a real user decision is missing, return needs_input with that exact decision. If work is broad, complete the safest useful slice and name the exact continuation. Keep enough evidence for DecisionsAI to checkpoint, retry, escalate, continue, or close the step.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).
The English summary is being prepared. Showing the original description.
Whole site or product — a full web accessibility (a11y) audit against WCAG 2.2, following the WCAG-EM methodology. Defines scope, samples representative pages and flows, runs the automated tier (`accessibility-scan`) and the hands-on manual tier (`accessibility-inspect`), and produces one conformance report. Grades each finding by severity and evidence basis, and states per-criterion conformance as pass, fail, or undetermined (needs a human). Use it for 'audit my site for accessibility', 'is this product accessible', 'a11y audit', 'WCAG or Section 508 conformance report', or any multi-page assessment. Assesses; does not fix (use `accessibility-fix`) or diff (use `accessibility-diff`). For a single page use `accessibility-scan`; for hands-on keyboard and screen-reader checks use `accessibility-inspect`.
The English summary is being prepared. Showing the original description.
Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.
The English summary is being prepared. Showing the original description.
Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.
The English summary is being prepared. Showing the original description.
One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names, roles and states from the accessibility tree, reflow and zoom, reduced motion, form errors, and target size. Grades each finding by evidence basis (verified / confirm-with-a-human / human-required) and severity, and closes every criterion in a ledger: verified, flagged, not exercised, or N/A. Locates and assesses; does not fix (use `accessibility-fix`). Use it for keyboard testing, focus-order checks, screen-reader or a11y-tree review, reflow and zoom at 200%, or 'is this operable, not just lint-clean'. The automated tier is `accessibility-scan`; `accessibility-audit` runs both across a sampled site.
The English summary is being prepared. Showing the original description.
One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can detect mechanically. Pass a URL, a config target name (e.g. `accesslint:accessibility-scan dev`), or nothing to use the default target from `accesslint.config.json`. Ensures a debuggable Chrome, runs the @accesslint/core engine over CDP, and returns a worklist of live-DOM WCAG 2.2 violations, each grounded to its DOM selector and source `file:line`. Locates; doesn't edit. Use it for 'is this page accessible', 'check a11y on this URL', 'find contrast and alt-text issues', or to verify a UI change. For hands-on keyboard and screen-reader checks use `accessibility-inspect`; for a whole site or product use `accessibility-audit`; to diff against uncommitted changes or a branch use `accessibility-diff`.
The English summary is being prepared. Showing the original description.