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 TalonT-Org/AutoSkillit --skill planner-refine-wpsgit clone --depth 1 https://github.com/TalonT-Org/AutoSkillitWrote 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/talont-org/autoskillit/planner-refine-wps)<a href="https://agentmods.dev/skills/talont-org/autoskillit/planner-refine-wps"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/planner-refine-wps/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/talont-org/autoskillit/planner-refine-wps"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/planner-refine-wps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.02544 |
| Opus 5.5 | $0.00012 | $0.01018 |
| Sonnet 5.5 | $0.00006 | $0.00509 |
| Haiku 4.5 | $0.00003 | $0.00254 |
Grade A, and why
planner-refine-wps 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
planner-refine-wps
L1 session that refines a combined_wps.json (a PlanDocument with all work
packages in WPElaborated form) by spawning one L0 subagent per phase in
parallel (batched to 6). Unlike the per-WP elaboration pass, this skill spawns
one L0 per phase (not per WP). Each L0 reviews ALL WPs in its assigned phase
against the full WP set, detecting cross-phase API mismatches, duplicate
deliverables, missing dependencies, and scope overlap. The L1 collects structured
suggestions, resolves conflicts, and writes refined_wps.json.
When to Use
- Launched by the L2 planner recipe after the parallel WP elaboration merge step
- Accepts
combined_wps.json,refined_plan.json, andrefined_assignments.json - Produces
refined_wps.jsonas input for downstream planner steps (e.g. reconcile_deps)
Arguments
- $1 — Absolute path to
combined_wps.json(PlanDocument withwork_packages: list[WPElaborated]) - $2 — Absolute path to
refined_plan.json(PlanDocument with phases as PhaseElaborated) - $3 — Absolute path to
refined_assignments.json(PlanDocument with assignments as AssignmentElaborated) - $4 — Absolute path to the run-scoped planner directory (e.g.,
{{AUTOSKILLIT_TEMP}}/planner/run-YYYYMMDD-HHMMSS). Output is written to$4/refined_wps.json.
Critical Constraints
NEVER:
- Write any file outside
$4/ - Directly modify
combined_wps.json($1) — always write a newrefined_wps.json - Allow an L0 subagent to write files directly (L0s return structured text only)
- Emit
refined_wps_pathbefore writingrefined_wps.json - Skip emitting
refined_wps_patheven if all L0s fail (write unchanged WPs, still emit) - Spawn more than 6 L0s in a single parallel batch
- Spawn one L0 per WP — L0s operate per PHASE
- Read
{{AUTOSKILLIT_TEMP}}artifacts not passed as positional arguments - Run subagents in the background (
run_in_background: trueis prohibited)
ALWAYS:
- Spawn one L0 per phase (NOT per WP) — each L0 reviews ALL WPs in its phase against the full WP set
- Validate each L0 response for
phase_id,wp_changes(array),cross_phase_deps(array),deliverable_conflicts(array),api_mismatches(array) - Log
WARNINGto stdout for any L0 response that fails validation (skip that phase) - Log
CRITICALto stdout for any L0 subagent that fails entirely (proceed with N-1 suggestions) - When two WPs claim the same deliverable file, assign ownership to the WP with the numerically earlier ID using natural sort (e.g.,
P1-A1-WP1beatsP2-A1-WP1) - Emit:
refined_wps_path = <absolute path to refined_wps.json>
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 · 219 lines · 31 tokens per session scan A 7e251a2363a0
planner-refine-wps is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 2,544 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
content-planner-auto
Use when auto-generate 30-day content calendars with pillar rotation, platform-optimized timing, multi-account rotation, seasonal Indonesian events, and PostBridge batch scheduling.
issue-triage
You are an expert at analyzing GitHub issue backlogs from a product manager's perspective. You don't just organize — you evaluate what matters most for project health and user experience, and you give actionable recommendations.
plan-insights
You are an expert at analyzing project delivery metrics from GitHub data. You produce actionable reports on milestone progress, delivery pipeline health, and stale work — giving PMs the data they need to make sprint decisions.
discussion-builder
You are an expert at creating structured GitHub Discussions from user input or planning documents. You interview the user, select the right template, and produce well-structured content for the discussion-manager agent to publish.
epic-to-project
You are an expert at structuring GitHub Projects (v2) from planning documents. You extract the high-level project structure — phases, priorities, custom fields — and map issues into a board layout.
plan-to-issues
You are an expert at extracting actionable tasks from technical planning documents and converting them into well-structured GitHub Issues.