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 Intai/story-flow --skill implement-story-markdowngit clone --depth 1 https://github.com/Intai/story-flowWrote 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/intai/story-flow/implement-story-markdown)<a href="https://agentmods.dev/skills/intai/story-flow/implement-story-markdown"><img src="https://agentmods.dev/badge/skills/intai/story-flow/implement-story-markdown/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/intai/story-flow/implement-story-markdown"><img src="https://agentmods.dev/badge/skills/intai/story-flow/implement-story-markdown.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 | $0.00017 | $0.00615 |
| Opus 5 | $0.00009 | $0.00308 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
Implement a story according to the requirements and tasks 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 9d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a story according to the requirements and tasks
Instructions
- The story should have tasks grouped by dependencies using the format from
story-flow:analyze-task-dependenciesskill. - You are an orchestrator, not an implementer.
- REQUIRED: Immediately delegate ALL tasks to subagents using the Task tool to run them in isolated context.
- FORBIDDEN tools for orchestrator (NEVER use directly):
- Glob, Grep, Read
- Write, Edit, MultiEdit
- WebSearch, WebFetch
- TaskCreate, TaskUpdate, TaskGet, TaskList
- Task with Explore subagent
- Instruct each subagent:
- When installing dependencies, use the latest stable version, or a higher patch version within the existing minor if the project pins one.
- After implementing UI according to UI design HTML files, verify by taking screenshots of both the UI and the design using
mcp__plugin_story-flow_chrome-devtools__navigate_pageandmcp__plugin_story-flow_chrome-devtools__take_screenshot. - For every source file created or modified, update the corresponding test file to achieve 100% coverage and ensure all linting warnings and errors are resolved.
- One test case per scenario/behavior, not one test per assertion.
- Combine test assertions for basic rendering into a single test - only separate tests when testing different states, behaviors, or edge cases.
- Every test must have assertions that verify the behavior described in its test name — not just that the code runs without crashing.
- No missing assertions: every test must contain at least one
expect()that checks a meaningful outcome. - Assertions must be correct: expected values must match the actual business logic, not be copied from implementation output without verification.
- No missing assertions: every test must contain at least one
- Report back to the orchestrator just "completed" or "failed". On success, strictly nothing else. On failure, include a brief summary of the issues encountered.
- When a story references the qa-tester subagent for planning BDD scenarios, use the qa-tester subagent and instruct it to load BOTH skills in this order using the Skill tool:
- First:
story-flow:plan-bdd-scenarios(plugin - general BDD planning protocol) - Then:
plan-bdd-scenarios(project-level - overrides/extends the plugin) - Confirm both skills are loaded before continuing with BDD planning.
- First:
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.
- 9d ago First seen · 45 lines · 17 tokens per session scan A 48d904a2cd41
Implement a story according to the requirements and tasks is a skill published in the GitHub repository Intai/story-flow (12 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 615 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
automation
Instructions for managing scheduled tasks through the host's structured automation tool, including reminders, delayed work, recurring checks, and result delivery.
find-leads
Find qualified B2B leads with OpenOutreach — run openoutreach find N [emails], read the CSV it prints on stdout, and hand the rows to whatever sends. Use when the user wants leads, prospects, an ICP-matched contact list, or asks what a campaign already has. Also covers first-run setup (openoutreach init), openoutreach…
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.