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/backloghq/backlog/refinenpx skills add backloghq/backlog --skill refinegit clone --depth 1 https://github.com/backloghq/backlogWhat 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 | $0.00046 | $0.00529 |
| Opus 5 | $0.00023 | $0.00264 |
| Sonnet 5 | $0.00009 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
refine 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine Backlog
Review the current backlog and improve its quality. This is a grooming pass — make tasks actionable, well-prioritized, and properly connected.
Process
-
Load the backlog — call
task_listwith filterstatus:pendingto get all pending tasks. -
Analyze each task for these issues:
Vague descriptions — tasks that are too broad or unclear. A good description starts with a verb and is specific enough that someone could implement it without asking questions. Flag tasks that need to be broken down or clarified.
Missing priorities — tasks without H/M/L priority. Suggest a priority based on the task's description and context.
Missing dependencies — tasks that logically depend on other tasks but don't have
dependsset. Look for ordering constraints (e.g., "write tests" should depend on the feature it tests).Tasks needing specs — complex tasks (multi-step, architectural, or ambiguous) that don't have a doc attached. Check with
task_countfilter+doc status:pendingand identify which tasks SHOULD have specs but don't.Stale tasks — tasks created long ago with no activity. Check
entrydates and annotations. Flag anything older than 30 days with no progress.Urgency mismatches — tasks with high urgency scores but low priority, or vice versa. These might need priority adjustments.
-
Present findings — group issues by category. For each issue, show the task ID, description, and the specific problem.
-
Fix with permission — for each category, ask if the user wants to apply the suggested fixes. Use the UUIDs from the
task_listresponse in step 1 for everytask_modify/task_doc_write/task_annotatecall — do not paraphrase or reuse UUIDs from earlier conversations. If you're unsure whether a UUID is still valid (e.g. after a long discussion), re-query withtask_infobefore mutating.
Guidelines
- Don't create new tasks — refinement improves existing ones
- Don't delete tasks — flag stale ones for the user to decide
- Suggest specific fixes, don't just list problems
- If the backlog is small and clean, say so — don't invent issues
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.
- 2d ago First seen · 38 lines · 46 tokens per session scan A 736e4d094efc
refine is a skill published in the GitHub repository backloghq/backlog (5 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 529 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.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.