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 agentmods add skills/mpazik/binder/refine-backlognpx skills add mpazik/Binder --skill refine-backloggit clone --depth 1 https://github.com/mpazik/BinderWhat 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 | $0.00029 | $0.01291 |
| Opus 5 | $0.00015 | $0.00646 |
| Sonnet 5 | $0.00006 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
refine-backlog 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine draft tasks to meet the Definition of Ready so they can move from draft to pending.
$ARGUMENTS
If specific tasks were given above, focus on those. Otherwise, work through the draft tasks listed below.
Draft Tasks
!binder search type=Task status=draft -f "key,title,taskType,priority,size,partOf" --format tsv
If no drafts are listed above, tell the user there's nothing to refine and stop.
Refinement Steps
For each task, work through these steps. Use binder read <key> --format yaml to inspect full details first.
Draft tasks from capture may already have fields set. Respect what's there -- only fill gaps unless user said otherwise.
1. Duplicate Check
- Compare against existing tasks, features, and concepts in Context below
- Also check cancelled tasks — don't recreate something deliberately cancelled
- If overlap found:
- Exact duplicate → cancel the draft, link to the existing one
- Partial overlap → merge the unique parts into the existing task, cancel the draft
- Related but distinct → keep both, link with
relatesTo
2. Classify
- Set
taskTypeif missing — match to the closest category (fix, feat, tweak, refactor, perf, agent, build, docs, test) - Set
sizeif missing — small: few files, no design decisions. medium: several files, 1-2 decisions. large: multiple commits, non-trivial decisions required. - Set
priorityif missing — p0=Blocker, p1=Urgent, p2=High, p3=Medium (default), p4=Low - Set
moduleif missing — which part of the codebase this belongs to - Set
sourceFilesif relevant files are obvious from the description
3. Describe
- Improve
titleif unclear (2-7 words, no verb prefix, max 70 chars) - Write
descriptionif missing (1-2 sentences with enough context)
4. Definition of Ready
Required for all tasks: title, taskType, size, priority, module, description.
Additional by size:
- medium+ tasks: add
constraints - large tasks: add
outOfScope
Additional by type:
- feat tasks: add
acceptanceCriteriawith testable scenarios - fix tasks: add
acceptanceCriteria(how to verify the fix) - refactor tasks: add
constraintsstating what behavior must not change
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.
- 3d ago First seen · 130 lines · 29 tokens per session scan A c898aefee993
refine-backlog is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 11d ago), licensed MIT. It adds 29 tokens to every session and 1,291 once invoked, about $0.0001 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.
Other skills, from other repositories
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…
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…
guideline-writing
Guideline-authoring craft for instruction SoTs (.claude/ guides, CLAUDE.md, plan files) — operative rules vs recital, MUST/SHOULD/MAY force tiers, pruning, bloat control, blind review protocol, deliberation-narrative ban. Use when writing, editing, or reviewing an agent instruction file, policy, runbook, command SoT…
journalism-writing
Journalism and argumentation writing craft — inverted pyramid, lede, nut graph, kicker, explainer framing, PAGE frames, Toulmin argument (claim/rebuttal/qualifier), Hegelian dialectic, BBC due impartiality. Use when writing or reviewing news/explainer pieces, landscape overviews, or issue analyses that fairly…
scholarly-citation
Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant attribution, citation typing (cites/references/contradicts/defines), source anchoring (Xanadu). Use when writing or reviewing a reference or synthesis page that attributes and…
consulting-writing
Management-consulting writing craft — McKinsey SCR (Situation·Complication·Resolution), Minto Pyramid/MECE, BCG bold-bullet executive summary, so-what upfront, numeric precision, Forrester Landscape. Use when writing or reviewing an executive summary for decision-makers or a roll-up/landscape overview, or when a…