<< All versions

Skill v1.0.1

currentAutomated scan100/100
thevibeworks/ccx/ccx-recap

+4 new

──Details
PublishedOctober 26, 2026 at 01:34 AM
Content Hashsha256:4637426fc5f74950...
Git SHAe257baa7ee97
Bump Typepatch
Compare with v1.0.0
──Files
Files (1 file, 5.7 KB)
SKILL.md5.7 KBactive
SKILL.md · 119 lines · 5.7 KB

version: "1.0.1" name: ccx-recap description: "Recap what a coding-agent session or time window actually did from ccx evidence: story, decisions, verified vs merely claimed, mistakes, cost. Use for 'what happened', 'what did it do', 'recap', 'summarize the session', 'what did I work on today/this week'. For 'what went wrong', use ccx-retro."


ccx-recap

One question: what did the agent actually do? Answer it with receipts, not vibes. The agent's own final message is a claim, not evidence — the recap is built from the trace.

Scope

TriggerEvidence source
/ccx-recapLatest session here: ccx trace
/ccx-recap <session-id>That session: ccx trace <id>
/ccx-recap today / week / monthThe whole fleet: ccx insight --scope <s> --all --json (every workspace's sessions digested), then ccx trace per session that decides the story

Timezone: preserve the user's. Warn when a --tz offset makes "today" differ from their local day (e.g. --tz +8 from a US machine).

This skill describes ccx >= 0.8. If a command or flag here is missing (unknown flag: --turn), the binary is older than the skill: upgrade ccx, then run ccx skills install — the binary embeds skills matching its own CLI surface.

Process

  1. Outline first. ccx trace --json (or ccx trace text) — every

turn and step headline with tools/edits/errors/cost. This always fits; read it whole. Steps are the agent's own narration at the moment it acted — that sequence IS the story skeleton.

  1. Pick what matters. Turns with edits, errors, linked commits,

high cost, user pushback, or human interventions (interrupts — the human pressed stop; denials — a tool call refused at the permission prompt; both are on turns, steps, and stats). Ignore command noise (is_command).

  1. Drill only there. ccx trace --turn N for full narration,

mutations, and error attribution. Raw text when needed: ccx view <session> --at <message_id> opens the cited message in context. When the story crosses sessions (a handoff picked up, a fork, a parallel agent), ccx related <session> says which sessions and how, with evidence — cite those anchors, do not guess the link.

  1. Verify before claiming. "Done" requires evidence: a passing

test step, a linked commit, a verification narration. Tag every important claim:

  • observed — tool output / git / trace shows it
  • agent-claimed — the agent said it; nothing independent checked
  • unverified — plausible, not checked
  1. Write the recap. Conversation reply first; offer an HTML

artifact for sessions worth keeping.

  1. Land it. A recap that ends at a chat reply evaporates — the

next session re-pays the full archaeology. Offer to write the distillation into whatever durable store the user already runs (devlog, memory file, wiki/vault page; never invent a new store). Keep the claims inline and cite the session as provenance: [ccx:<session-id> #turn.step] — anyone can re-open the receipt with ccx trace <session-id> --turn N. If the user declines or has no store, the reply is the deliverable.

The 60-second test

A reader must know, within a minute: what was asked, what the agent did about it, the 3-5 decisions that shaped the work, what is verified vs claimed, what it cost, and what is still open. If the recap can't produce that paragraph, it is not done.

Format (conversation or HTML):

Recap — <session/scope> | <duration> | $<cost> | <files> files | <errors> tool errors
What happened 3-8 sentences, chronological, cited [#turn.step]
Decisions the real ones only, with the rejected alternative
Verified vs claimed anything important that lacks evidence, flagged
Still open unfinished work, unverified claims, warnings
Numbers small table: turns, steps, edits, errors, cost

Citations are #turn.step (e.g. #133.9). Copy trace warnings into the recap — evidence gaps are part of the answer.

Multi-session (today / week / month)

The subject is everything the human did with agents in the window — every workspace, every provider — not the repo you happen to be in. ccx insight --scope <s> --all --json (ccx.insight.v1) is the whole evidence set and it fits: read it whole before deciding what matters.

  1. metrics and workspaces[] say where the work went and what it

cost; quote cost with cost_coverage (an unpriced model is not a free one).

  1. sessions[] carry each session's human prompts[] (intent, cited

by session:line), final_answer (agent-claimed), edits, commits, interrupts/denials, cost_usd + cost_status, and relation (a session that started before the window is a long-running container, not this window's work).

  1. Group sessions into workstreams by workspace and prompt content,

not by session count. Then ccx trace <id> only the 3-5 sessions that decide the story (cost, edits, commits, interventions, or the human's stated interest) and verify their claims.

  1. Write the recap per workstream: what was asked, what the agent

did, verified vs claimed, still open. Never re-bucket ccx log records yourself; never let one workspace stand in for the fleet.

For a human review surface, write the HTML cockpit described in HTML-REPORT.md: judgment on top of the digest, into the insights dir so it shows at /insights in ccx web.

Hard rules

  • No judgment without a citation. No citation, say "unverified".
  • Do not paste transcripts; the recap is the distillation.
  • Numbers come from the trace/insight, never estimated.
  • The final assistant message is input, not truth: check it against

the evidence like any other claim.

← v1.0.0All versions