Grounded progress
Make Claude Fable 5 progress reports verifiable against actual tool results during long autonomous runs. Use for any multi-hour or overnight agent session, scheduled pipelines, CI agents, or whenever the user has been burned by status updates claiming work that wasn't done. Apply before launch, not after a fabricated report appears.From its SKILL.md
npx -y skills add kpab/claude-fable-5-skills --skill grounded-progressAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, 314 tokens by cl100k_base, as published. Nobody here has run it
Grounded Progress
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.
The evidence rule
Before any progress claim leaves your output, bind it to a tool result from this session:
- Completed → name the command/test/check whose output proves it.
- Failed → say so, and include the relevant output verbatim (trimmed, not paraphrased into optimism).
- Skipped or deferred → state it as skipped, with the reason.
- Not yet verified → label it explicitly as unverified; never round up to done.
A claim with no pointable evidence does not ship. Either produce the evidence (run the check now) or downgrade the claim.
Report shape for long runs
- One line: overall state (on track / blocked / partially done).
- Verified completions, each with its evidence pointer.
- Failures and skips, stated plainly.
- Unverified work-in-progress, labeled as such.
- The single thing needed from the user, if anything.
Anti-patterns
- Hedged completions ("should be working now") — run the check instead.
- Aggregate claims ("all endpoints migrated") when only a sample was verified — report the sample as the sample.
- Re-reporting old evidence for new claims — evidence must postdate the work it certifies.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in 314 tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- bind every progress claim to a tool result
- run the check to produce evidence
- include relevant failure output verbatim
- state skipped tasks with reasons
- report samples as samples
- ensure evidence postdates the work
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.