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/guyroyse/chiastic-coding-plugin/story-orchestratornpx skills add guyroyse/chiastic-coding-plugin --skill story-orchestratorgit clone --depth 1 https://github.com/guyroyse/chiastic-coding-pluginWrote 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/guyroyse/chiastic-coding-plugin/story-orchestrator)<a href="https://agentmods.dev/skills/guyroyse/chiastic-coding-plugin/story-orchestrator"><img src="https://agentmods.dev/badge/skills/guyroyse/chiastic-coding-plugin/story-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00841 |
| Opus 5 | $0.00016 | $0.00420 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
story-orchestrator 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Orchestrator
You orchestrate a TDD pair programming workflow. You receive a Gherkin feature file, decompose it into behaviors, and drive a pair of agents through red/green/refactor cycles for each one.
Process
- Parse
$ARGUMENTSto extract the feature file path and any optional flags (--max-cycles <n>,--no-squash). Flags not provided should use defaults. - Decompose the scenarios into discrete behaviors to implement — a scenario may yield one or more tasks.
- Create a task for each behavior using TaskCreate, with dependencies so they are worked in order.
- For each behavior, in sequence:
a. Update the task to in_progress.
b. Run
pair.jswith the behavior description. c. Parse the JSON result from the last line of output. Handle based on thestatusfield (see Handling results below). - When all tasks are complete, report a summary of what was built.
Running the pair
Invoke the pair script from the skill directory:
${CLAUDE_SKILL_DIR}/scripts/pair.js --behavior "<behavior description>" [--maxCycles <n>] [--noSquash]
Pass through --maxCycles and --noSquash if they were provided in $ARGUMENTS. Otherwise, omit them and let pair.js use its defaults.
The script manages two agents (Alice and Bob) through red/green/refactor cycles. It returns when the test writer signals there are no more tests to write for the behavior, or when max cycles is reached.
The script logs progress to stdout as it runs (cycle numbers, agent turns, commit messages). You don't need to parse this — it's useful context if something goes wrong and you need to report to the user.
The script outputs a JSON result as its last line:
{ "behavior": "...", "status": "complete", "commits": 3, "error": null }
The status field will be one of:
complete— the behavior was fully implemented.max-cycles— the pair ran out of cycles without completing.error— the pair encountered a failure (seeerrorfield for details).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 69 lines · 32 tokens per session scan A c1605e075825
story-orchestrator is a skill published in the GitHub repository guyroyse/chiastic-coding-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 841 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 2026-08-30.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.