From fable5-skills
Makes progress reports verifiable by binding claims to tool results during long autonomous runs. Prevents fabricated status updates in CI agents or overnight sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fable5-skills:grounded-progressThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
On long runs the failure mode isn't usually bad work — it's a report that drifts from the work: "tests passing" when they were never run, "deployed" when the command errored. The fix is an evidence rule applied at report time.
On long runs the failure mode isn't usually bad work — it's a report that drifts from the work: "tests passing" when they were never run, "deployed" when the command errored. The fix is an evidence rule applied at report time.
Before any progress claim leaves your output, bind it to a tool result from this session:
A claim with no pointable evidence does not ship. Either produce the evidence (run the check now) or downgrade the claim.
npx claudepluginhub kpab/claude-fable-5-skills --plugin fable5-skillsBinds every progress claim to an actual tool result from the session. Use for multi-hour agents, overnight pipelines, or CI runs where status updates have previously claimed work not done.
Validates agent completion claims against evidence trail, catching unsubstantiated claims like 'tests pass' or 'fixed' without proof. Auto-fires at workflow end.
Validates deliverables and builds evidence trails for multi-agent handoffs, with fidelity checks for compressed outputs and structured disagreement reporting.