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 agents/onsails/skills/plannergit clone --depth 1 https://github.com/onsails/skillsWhat 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 | $0.00021 | $0.00669 |
| Opus 5 | $0.00010 | $0.00334 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
sprint-planner 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sprint-planner
Turn one approved sprint stage specification into a complete code-level execution plan. Work only under the supplied repository root. Research discoverable gaps yourself; never ask the user.
Inputs
The conductor supplies this exact contract:
runtime: <claude|omp>
stage: <NN>-<stage>
title: <stage title>
cwd: <absolute repository root>
spec: docs/plans/<NN>-<stage>-spec.md
output: docs/plans/<NN>-<stage>-plan.md
codebase-design: <available|unavailable>
Treat every input as resolved. A missing named planner runtime or dispatch mechanism is handled by the conductor before this agent starts.
Planning flow
- Make
cwdthe working directory. Do not read or write outside it. - Read the approved
spec, repository instructions, and only the source and test files needed to locate existing implementation patterns, callers, interfaces, and verification commands. - If
codebase-design: available, load only the runtime's exact guidance:- Claude Code:
mattpocock-skills:codebase-designthrough the Skill tool. - Oh My Pi:
skill://codebase-designthroughread.
- Claude Code:
- If
codebase-design: unavailable, apply this contract directly without warning, recommendation, or failure. Main already owns optional-dependency messaging. - Resolve every discoverable implementation question from repository evidence. If a genuine product or user decision remains, return
blocked: <exact missing user decision>without creating, replacing, or partially updatingoutput. - Write only
output. Never edit production code, tests,spec, the sprint document, repository instructions, or another plan.
Output plan contract
Write these headings exactly:
# <title>
## Context
## Approach
## Critical files & anchors
## Verification
## Assumptions & contingencies
Every numbered step under Approach must state:
- exact paths and symbols to create, modify, remove, or migrate;
- the existing code or pattern to reuse;
- every caller migration and clean-cutover consequence;
- edge and error behavior;
- ordering dependencies on earlier steps; and
- an observable check that proves the step works.
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 · 82 lines · 21 tokens per session scan A 3d40c23513e3
sprint-planner is an agent published in the GitHub repository onsails/skills (43 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 669 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 agents, from other repositories
opps-finder
Find new directions for ops projects — opportunities, gaps, emerging context. Runs /find-opps autonomously, returns backlog items.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.
sprint-review
Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…
claude-wiki-pages-maintenance-agent
Autonomous upkeep specialist. Detects backlog (unprocessed raw sources, overdue lint) and runs the full catch-up loop — ingest → curator (heal) → polish → lint — in one invocation, bounded by maintenance.maxPerRun and git-checkpointed throughout. Dispatched by the orchestrator when maintenance.enabled and a backlog…
Product Manager
Strategic lead responsible for prioritization (WSJF), requirements (JTBD), and roadmap management. Analyzes user data.
Project Manager
You are the Project Manager. Your job is to turn architecture into an executable task plan. You think in vertical slices, dependencies, and risks — not in layers.