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.
npx skills add mpazik/Binder --skill capture-taskgit clone --depth 1 https://github.com/mpazik/BinderWrote 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.
[](https://agentmods.dev/skills/mpazik/binder/capture-task)<a href="https://agentmods.dev/skills/mpazik/binder/capture-task"><img src="https://agentmods.dev/badge/skills/mpazik/binder/capture-task/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.
<a href="https://agentmods.dev/skills/mpazik/binder/capture-task"><img src="https://agentmods.dev/badge/skills/mpazik/binder/capture-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01465 |
| Opus 5.5 | $0.00019 | $0.00586 |
| Sonnet 5.5 | $0.00010 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00146 |
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 1mo 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.
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 prefixtaskType(required) — fix, feat, tweak, refactor, perf, agent, build, docs, testdescription— 1-2 sentences with enough contextdetails— steps to reproduce, useful context, skip obvious backgroundpriority— p0=Blocker, p1=Urgent, p2=High, p3=Medium (default), p4=LowsourceFiles— 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 slugmodule— which part of the codebase this belongs tosize— small: few files, no design decisions. medium: several files, 1-2 decisions. large: multiple commits, non-trivial decisionspriority— if user didn't specify, default p3acceptanceCriteria— optional, testable scenariosconstraints— optional, what must hold or not changeoutOfScope— 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.
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.
- 1mo ago First seen · 144 lines · 48 tokens per session scan A fc983bda3d99
capture-task is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 28d ago), licensed MIT. It adds 48 tokens to every session and 1,465 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
kanban-tasks
A task-board workflow for breaking work into cards and moving them through stages such as inbox, ready, doing, review, and done. It also includes a background service and a web interface for the board.
pad
Work with the user's Pad workspaces through the Pad tools. Find, read, create and update tasks, bugs, ideas, plans and docs; comment on them, link them, and see what to work on next. Use it whenever the user talks about their Pad projects or items.
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…
graft
Persistent graph memory shared across conversations and agents. Graft is a prompter, not a cache: it hands you notes that may be close to the problem in front of you, and a close note is already a win - it gives you a starting point and reminds you what was decided before. Search it before non-trivial work, and write…
handoff-inbox-drain
Use when draining a Brigade handoff review inbox - triage drafts with allowlist-bound Brigade handoff commands, grounded edits that cite on-disk content, archive-only retention, and reinforce-in-place when ingest already matched a known fact (#724). Never delete, remove, or prune.
memory-audit
Maintenance pass + health check of the graft graph. Runs the graft maintain loop: checks what is due, applies the mechanical cleanup, then adjudicates every maintenance candidate (near duplicates, supersessions, contradictions, memories whose source file changed or disappeared, keyword variants, stale low-value notes)…