recap SKILL.md skillA
recap from parcha-ai/parcha-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add parcha-ai/parcha-skills/recap@git:20260714.1ba3acePins git:20260714.1ba3ace in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- parcha-ai/parcha-skills
- Path
recap/skills/recap/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260714.1ba3ace, committed Jul 14, 2026
- First version recorded
- Jul 14, 2026
- Size
- 11,746 bytes
- Repository stars
- 65
- License
- MIT
Reconstruct what a Claude Code or Codex agent actually did during one exact session, including goals, decisions, actions, file and git changes, tests, failures, recoveries, final state, and open work. Use when the user says "/recap", "recap this session", "what did this agent do", "give me the full handoff", or asks for an evidence-backed account of a long-running coding-agent session. Use Recall for prior-session discovery; use Recap after a session is identified. Never use it to expose…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# /recap — evidence-backed session comprehension Recap explains one coding-agent session from end to end. It treats the transcript as an event source, repository state as corroborating evidence, and the active agent as the semantic synthesizer. The wrapper collects and validates evidence; it never calls a model. ## Pick the boundary - With no target, recap the exact current native session. `CODEX_THREAD_ID` is authoritative for Codex. An exact Claude session ID is authoritative when the harness exposes one. - For a prior session, first use `$recall` to find it, then pass its exact path or stable receipt. - Match the requested harness and time boundary. If the user asks for a prior Claude session, do not substitute `--current` or a Codex result: search Recall with `--harness claude` plus the relevant cwd/branch, then pass the winning exact path or receipt. Fail if no candidate matches. - Keep resumed sessions, subagents, and continuations separate by default. Include them only when the user asks, and label every boundary independently. - If identity is ambiguous, stop with the candidates. Never choose the nearest transcript by time. ## Collect a private manifest …
Read the whole file at its exact version.
How to install
mdr add parcha-ai/parcha-skills/recap@sha256:ea5bfd3ecef33143The line at the top of this page pins the label git:20260714.1ba3ace, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_azdwckywjtllusya)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on Jul 14, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260714.1ba3ace latest | 2026-07-14 | 1ba3ace | 11,746 B | A | view · diff |
| git:20260714.5318db9 | 2026-07-14 | 5318db9 | 7,455 B | A | view · diff |
| git:20260714.5430ae0 | 2026-07-14 | 5430ae0 | 9,290 B | A | view · diff |
| git:20260714.5f3deb8 | 2026-07-14 | 5f3deb8 | 10,691 B | A | view · diff |
| git:20260714.72d7a44 | 2026-07-14 | 72d7a44 | 11,456 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11746 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
parcha-ai/parcha-skills · 65 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_azdwckywjtllusya GET https://markdownregistry.com/api/v1/resolve?ref=parcha-ai/parcha-skills/recap GET https://markdownregistry.com/api/v1/blob/ea5bfd3ecef3314398b9f15fb4d42b3528526fbc1f2dbc24ea5fa6bc2cf0f651
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from parcha-ai/parcha-skills
Every file in parcha-ai/parcha-skills