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 implement-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/implement-task)<a href="https://agentmods.dev/skills/mpazik/binder/implement-task"><img src="https://agentmods.dev/badge/skills/mpazik/binder/implement-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/implement-task"><img src="https://agentmods.dev/badge/skills/mpazik/binder/implement-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 | $0.00051 | $0.00633 |
| Opus 5.5 | $0.00020 | $0.00253 |
| Sonnet 5.5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
implement-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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work on a task. Provide a task key, or omit to pick from the lists below.
$ARGUMENTS
If a task key was given above, read it with binder read <key> --format yaml. If the key doesn't exist, tell the user and stop. Otherwise, pick from the lists below and then read it.
Check the task's status:
- draft — needs refinement first, not ready to work on. Tell the user.
- complete or cancelled — nothing to do. Tell the user.
- pending, active, paused — proceed.
Active Tasks
!binder search type=Task status=active -f "key,title,taskType,size,priority,module" --format tsv
Pending Tasks
!binder search type=Task status=pending -f "key,title,taskType,size,priority,module" -o "!priority" --format tsv
Choosing a guide
After reading the task, decide which guide to load based on what it needs right now.
| Condition | Guide |
|---|---|
fix task, rootCause empty |
guides/investigate.md — find root cause |
requires or relatesTo links to a Problem record (check linked keys) |
guides/discuss.md — resolve open questions |
specification empty, and task is medium+, refactor, or agent |
guides/design.md — produce a specification |
| fix/feat/refactor/test task that still needs tests | guides/write-tests.md — write tests |
| None of the above apply | guides/implement.md — implement |
Multiple conditions can match. Start with the topmost one that applies, or follow the user's direction. Read the guide, then follow its instructions.
After completing a guide, re-read the task and check the table again. If another condition applies, load that guide next. If no conditions match, go to implement.
Updating multi-line fields
For single-value fields: binder update <key> field=value
For multi-line or rich text fields (rootCause, specification, details, etc.), use a transaction file:
- author: agent
records:
- $ref: <key>
specification: |
## Approach
...
What ships with it
7 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.
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 · 63 lines · 51 tokens per session scan A c9b66b7b4ff6
implement-task is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 25d ago), licensed MIT. It adds 51 tokens to every session and 633 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)…