capture-task

A task-capture skill that turns a rough idea, bug report, or specification into a draft task record. It assigns a short branch-friendly key and records details such as type, priority, files, and acceptance criteria when supported by the input.

In plain words
What is it for?
Adding backlog tasks, logging bugs, recording feature ideas, and capturing relevant reproduction steps, source files, constraints, or completion conditions.
Why use it?
It prevents useful work from being lost in informal notes and separates what the user said from details inferred by the agent. It also gives tasks a consistent structure for later work.

Skill for Claude CodeCodex

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/mpazik/binder/capture-task
Any agent
npx skills add mpazik/Binder --skill capture-task
Clone the repo
git clone --depth 1 https://github.com/mpazik/Binder

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,465 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 $0.00048 $0.01465
Opus 5 $0.00024 $0.00732
Sonnet 5 $0.00010 $0.00293
Haiku 4.5 $0.00005 $0.00146

Measured 2d ago against content hash fc983bda3d99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capture-task 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 2d 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.

examples/workflow/skills/capture-task/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture the following as a Task in the binder knowledge graph.

$ARGUMENTS

If no input was given above, ask the user what to capture.

Key Convention

Format: {taskType}-{short-slug}, kebab-case. Must be usable as a git branch name. 2-7 words, max 70 chars.

Examples: fix-sync-null-values, feat-export-csv, tweak-sidebar-padding, docs-api-reference

Fields

Captured — taken directly from user input. Only include what the user actually said:

  • title (required) — 2-7 words, max 70 chars, no verb prefix
  • taskType (required) — fix, feat, tweak, refactor, perf, agent, build, docs, test
  • description — 1-2 sentences with enough context
  • details — steps to reproduce, useful context, skip obvious background
  • priority — p0=Blocker, p1=Urgent, p2=High, p3=Medium (default), p4=Low
  • sourceFiles — paths to relevant source files, when the user mentions them

Inferred — derived by the agent. Clearly marked so the user can correct. For acceptanceCriteria, constraints, and outOfScope: only propose when obvious from context. Better empty than hallucinated.

  • key — generated from taskType + title slug
  • module — which part of the codebase this belongs to
  • sizesmall: few files, no design decisions. medium: several files, 1-2 decisions. large: multiple commits, non-trivial decisions
  • priority — if user didn't specify, default p3
  • acceptanceCriteria — optional, testable scenarios
  • constraints — optional, what must hold or not change
  • outOfScope — optional, what this task deliberately does not cover

Run binder schema --types Task for the full Task schema and available field values.

Flow

1. Parse and assemble

Extract fields from user input. Infer what you can. Check for duplicates against Context below.

If a duplicate is found:

  • Exact duplicate — tell the user, don't create. Link to the existing task.
  • Partial overlap — tell the user. They can merge into the existing task or keep both.
  • Related but distinct — note it. If created, link with relatesTo.

Read the full file on GitHub · 144 lines

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. 2d ago First seen · 144 lines · 48 tokens per session scan A fc983bda3d99

Subscribe to this mod's changes

capture-task is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 10d ago), licensed MIT. It adds 48 tokens to every session and 1,465 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 2026-08-30.

Related

Other skills, from other repositories

phase-orchestrator

Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and phase-final-reviewer skills and consumes…

hraness/kb · 101 tokens

phase-implementer

Implements exactly one phase of a multi-phase plan during a phase-orchestrator run. Use when a plan/checklist phase needs to be built: the parent supplies the plan path, phase scope, prior-phase results, repo rules, and commit policy. Edits files directly; never commits unless commit authority is explicitly delegated.…

hraness/kb · 86 tokens

engraphis-memory

Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…

Coding-Dev-Tools/engraphis · 134 tokens

starcat-support-project-create

创建并登记 Starcat supports 独立支撑项目的完整流程。用于用户要在 supports/ 下新增 API、CLI、Launcher、浏览器扩展、Homebrew tap、文档、网站或其他独立仓库,并要求补齐开源治理文件、中英文 README、Starcat 营销区块、GitHub 模板/Actions、clone-all.sh、sync-starcat-readme-promo.py 和 supports 跨项目文档的场景。.

starcat-app/Starcat · 105 tokens

encyclopedia-writing

Encyclopedic neutral-reference writing craft — NPOV (attribute facts not opinions, due weight, neutral faction labels, verdict restraint), summary style and Coatrack avoidance, wikilink conventions (link density, first-mention, slug alias, abbreviation glossing). Use when writing or reviewing a neutral…

alfadur7/llm-wiki-newsroom · 95 tokens

forward-plan

Use when turning Brigade's native ready set, outcome rank, and ROADMAP.md into a dependency-filed plan artifact under .brigade/work/plans/ - propose GraphTrail-derived edges (blocks from def/use, conflicts-with from write overlap) marked derived and requiring confirmation. Degrade cleanly when GraphTrail is…

escoffier-labs/brigade · 73 tokens