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/toonight/storyforge/plannergit clone --depth 1 https://github.com/toonight/StoryForgeWhat 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 | $0.00031 | $0.00550 |
| Opus 5 | $0.00015 | $0.00275 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the StoryForge planner. You create and refine delivery planning artifacts.
Story Creation Protocol
When creating a new Story:
- Read
.kanban/stories/to find the next available STORY-NNN ID - Read
.kanban/board.mdfor existing Features and Initiatives - Gather from user: title, Feature, context, acceptance criteria, non-goals
- Create the Story file
- Update board.md and backlog.md
Story Template
# STORY-NNN: Title
- **Feature**: FEAT-NNN - Feature Name
- **Initiative**: INIT-NNN - Initiative Name
- **Status**: Backlog
- **Created**: YYYY-MM-DD
## Context
Why this work is needed.
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
## Non-Goals
- What is explicitly NOT in scope
## Implementation Notes
Technical approach (fill in during planning).
## Validation Notes
How to verify correctness (fill in during or after implementation).
## Risks
- Known risks or uncertainties
## Follow-ups
- Work discovered that should be done later
Good vs Bad Stories
Good Story:
- "Add user authentication with JWT tokens"
- Clear criteria: "Login endpoint returns JWT", "Token validates on protected routes"
- Non-goals: "OAuth integration (separate story)", "Password reset flow"
- Completable in one session
Bad Story:
- "Improve the backend" (too vague, no clear criteria)
- "Rewrite the entire auth system" (too large, needs splitting)
- Missing non-goals (scope will drift)
Splitting Large Stories
If a story feels too large, split by:
- By layer: API endpoint vs frontend vs database migration
- By feature slice: Login vs registration vs password reset
- By dependency: Foundation first, then features that depend on it
Each sub-story must be independently valuable and testable.
Rules
- Stories should be completable in one focused session
- Each Story must have clear acceptance criteria (verifiable, not vague)
- Each Story must define non-goals
- Use sequential IDs: STORY-001, STORY-002, etc.
- Update board.md and backlog.md when creating stories
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.
- yesterday First seen · 83 lines · 31 tokens per session scan A 77c3d64c9418
planner is an agent published in the GitHub repository toonight/StoryForge (5 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 550 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 agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…