replay
Skill0 starsChanged 52 days agoMITView on GitHub
Replay a recorded ArcheFlow run: decision timeline and weighted what-if over the reviewers' verdicts. Usage: /archeflow:replay <run_id> [--timeline|--whatif|--compare] [--weights role=w,...] <example>User: "/archeflow:replay 2026-04-06-jwt-auth"</example> <example>User: "/archeflow:replay 2026-04-06-jwt-auth --whatif --weights guardian=2,sage=0.5"</example>
7 other projects use a version of this.
Adopted by
Most recently taken up by
- quickchatai/quickreviewtheir own version, first seen Nov 15, 2026
- sanjaibalajee/skillstheir own version, first seen Nov 8, 2026
- icarloscornejo/doertheir own version, first seen Nov 7, 2026
- cukas/remembralltheir own version, first seen Nov 1, 2026
- amajorai/replay.mdtheir own version, first seen Oct 13, 2026
- tuo-lei/vibe-replaytheir own version, first seen Aug 30, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- entireio/skills★ 239same name
- tuo-lei/vibe-replay★ 39same name
- quickchatai/quickreview★ 9same name
- cukas/remembrall★ 6same name
- amajorai/replay.md★ 1same name
- sanjaibalajee/skills★ 1same name
- icarloscornejo/doer★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/archeflow.mdcCursor rule
- archeflow-reviewSkill
- archeflow-runSkill
- archeflow-sprintSkill
- act-phaseSkill
- autonomous-modeSkill
- check-phaseSkill
- cost-trackingSkill
- custom-archetypesSkill
- dagSkill
- domainsSkill
- git-integrationSkill
- initSkill
- memorySkill
- multi-projectSkill
- presenceSkill
- progressSkill
- reportSkill
- reviewSkill
- runSkill
- scanSkill
- scoreSkill
- shadow-detectionSkill
- sprintSkill
- statusSkill
- templatesSkill
- using-archeflowSkill
- workflow-designSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
Write the data object ({"archetype": ..., "input": ..., "decision": ..., "confidence": 0.85}) to .archeflow/artifacts/<run_id>/event.json …
- Distinctive: line 34
Never paste summaries or task text into the command line itself.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ArcheFlow Run Replay
Inspect a run logged in .archeflow/events/<run_id>.jsonl: which roles drove the outcome, and
what a weighted vote would have decided. Only accept run IDs made of letters, digits, ., _, -.
Commands (from the project root)
| Action | Command |
| Timeline (default) | <archeflow-root>/lib/archeflow-replay.sh timeline <run_id> |
| What-if | <archeflow-root>/lib/archeflow-replay.sh whatif <run_id> [--weights guardian=2,sage=0.5] [--threshold 0.5] [--json] |
| Both | <archeflow-root>/lib/archeflow-replay.sh compare <run_id> [--weights ...] |
- Timeline lists
decision.pointevents and the Check-phasereview.verdictevents. - What-if takes the last
review.verdictper role. Original outcome: any non-approval blocks. Replay: each reviewer contributes weight x (1 if not approved, else 0); BLOCK if the weighted mean is at or above the threshold (default 0.5). --jsonprints machine-readable output.
Recording decisions (during a run)
/archeflow:run records decision.point events after routing, fast-path and escalation choices.
Write the data object ({"archetype": ..., "input": ..., "decision": ..., "confidence": 0.85})
to .archeflow/artifacts/<run_id>/event.json with your file tool, then:
<archeflow-root>/lib/archeflow-event.sh <run_id> decision.point <phase> <role> "$(cat .archeflow/artifacts/<run_id>/event.json)".
Never paste summaries or task text into the command line itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.