capture

capture is a skill for Claude Code, Codex from foliveira/harmonia. It costs 34 tokens per session (523 once invoked), scanned A, original, MIT.

A closing workflow that records useful project learnings and prepares structured commits after developer acceptance.

In plain words
What is it for?
Use it after implementation to verify acceptance, save learnings in the appropriate memory, and finish the commits.
Why use it?
It prevents lessons from being lost and stops changes from being committed before the developer confirms they work as intended.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the harmonia plugin — 16 skills, 12 agents, 1 hook shipped together

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.

agentmods
npx agentmods add skills/foliveira/harmonia/capture
Any agent
npx skills add foliveira/harmonia --skill capture
Clone the repo
git clone --depth 1 https://github.com/foliveira/harmonia

Made for: Claude Code, Codex.

Or install harmonia, the plugin that ships this one along with the rest of its 16 skills, 12 agents, 1 hook.

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.

agentmods badge for capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/foliveira/harmonia/capture.svg)](https://agentmods.dev/skills/foliveira/harmonia/capture)
Your own site
<a href="https://agentmods.dev/skills/foliveira/harmonia/capture"><img src="https://agentmods.dev/badge/skills/foliveira/harmonia/capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00523
Opus 5 $0.00017 $0.00262
Sonnet 5 $0.00007 $0.00105
Haiku 4.5 $0.00003 $0.00052

Measured 3d ago against content hash 700ef07e6233, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capture 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 3d ago.

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.

skills/capture/SKILL.md · 17 lines

What it actually says

Your working contract is the 4 rules; their digest is injected at session start - read ${CLAUDE_PLUGIN_ROOT}/core/RULES.md in full only if that digest is not in your context. Read the capture stage from ${CLAUDE_PLUGIN_ROOT}/core/lifecycle.yaml - its agent sequence ends with the committer by contract; do not hardcode.

  1. Workspace: bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh resolve --repo . (later stage: never mints; surface ambiguity or no-active-task and stop).
  2. Acceptance gate: capture requires the acceptance in-artifact (workspace:accepted), written only by the developer after they exercised the built behavior and it matches intent. Verify it: bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh verify-acceptance --repo .. Gate on the exit: any non-zero exit means refuse - surface the script's own message verbatim and stop, do not dispatch the curator; only a zero exit proceeds. The message states the remedy: no marker means the developer records acceptance via /harmonia:accept; a stale digest mismatch means the diff moved after acceptance, so the developer exercises the current behavior and re-accepts via /harmonia:accept (the marker must digest the diff it attests); a live rejection clears via /harmonia:accept or /harmonia:abandon. Never run accept on the developer's behalf - acceptance is a human act.
  3. Dispatch the knowledge curator with the verdict, scope, and diff-summary paths. It drafts learnings and writes each through bash ${CLAUDE_PLUGIN_ROOT}/bin/memory/capture.sh with an explicit --tier decision and --client flag where applicable - client content never reaches the global tier (R21).
  4. Dispatch the committer with boundary.md, diff-summary.md, and the verdict: structured, single-concern commits whose messages communicate intent (R6); nothing outside the boundary, never workspace files.
  5. Close the task: bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh complete --repo . (writes the completion marker so resolution skips this workspace).

Pass workspace paths, not prose recaps (R8). Orchestrate only (R9).

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.

  1. 3d ago First seen · 17 lines · 34 tokens per session scan A 700ef07e6233

Subscribe to this mod's changes

capture is a skill published in the GitHub repository foliveira/harmonia (2 stars, last pushed 18d ago), licensed MIT. It adds 34 tokens to every session and 523 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

writing-workflow-skills

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

JetBrains/thinkrail · 60 tokens

writing-specs

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

JetBrains/thinkrail · 59 tokens

clarify

Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates automatically when ambiguity persists.

mag123c/toktrack · 43 tokens

auditing-aws-s3-bucket-permissions

Systematically audit AWS S3 bucket permissions to identify publicly accessible buckets, overly permissive ACLs, misconfigured bucket policies, and missing encryption settings using AWS CLI, S3audit, and Prowler to enforce least-privilege data access controls.

adriannoes/awesome-agentic-ai · 62 tokens

containing-active-breach

Executes containment strategies to stop active adversary operations and prevent lateral movement during a confirmed security breach. Implements short-term and long-term containment using network segmentation, endpoint isolation, credential revocation, and access control modifications. Activates for requests involving…

adriannoes/awesome-agentic-ai · 73 tokens