A tool for reconstructing what a coding agent did during one specific session, including its decisions, file changes, tests, failures, and unfinished work.

Use it for a current-session recap, a prior-session handoff, or an evidence-based account of what changed.

It turns scattered session records and repository evidence into a clear handoff, while keeping separate sessions and agents from being mixed together.

recap — Skill for Claude Code and Codex by Parcha-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Parcha-ai/parcha-skills --skill recap

Clone the repo

git clone --depth 1 https://github.com/Parcha-ai/parcha-skills

Made for: Claude Code, Codex.

Or install recap, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/recap/github.svg)](https://agentmods.dev/skills/parcha-ai/parcha-skills/recap)

Your own site

<a href="https://agentmods.dev/skills/parcha-ai/parcha-skills/recap"><img src="https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/recap/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/parcha-ai/parcha-skills/recap"><img src="https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/recap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,511 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 84
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00122	$0.02511
Opus 5	$0.00061	$0.01256
Sonnet 5	$0.00024	$0.00502
Haiku 4.5	$0.00012	$0.00251

Measured 12d ago against content hash ea5bfd3ecef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

recap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/accounting.py, scripts/event_ledger.py, scripts/git_provenance.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

recap/skills/recap/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/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

Run from this skill directory:

python3 scripts/recap.py collect --current --output ~/.recap/current.json
python3 scripts/recap.py collect --session <exact-session-path> --output ~/.recap/prior.json

For an exact main session plus its native subagents, its explicit Codex fork/continuation chain, or both, collect a boundary set. Recap asks Recall to prove native relationships and keeps every transcript in its own manifest and ordinal space:

python3 scripts/recap.py collect-set --current --include-children --output ~/.recap/with-children.json
python3 scripts/recap.py collect-set --session <exact-path> --chain --output ~/.recap/chain.json
python3 scripts/recap.py collect-set --session <exact-path> --chain --include-children \
  --output ~/.recap/full-run.json
python3 scripts/recap.py validate-set ~/.recap/full-run.json

Read the full file on GitHub · 222 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 222 lines · 122 tokens per session scan A ea5bfd3ecef3

Subscribe to this mod's changes

recap is a skill published in the GitHub repository Parcha-ai/parcha-skills (59 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 2,511 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens