Borrowing it
Nothing to install: this file belongs to jerseycheese/Narraitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jerseycheese/Narraitor/main/.claude/skills/narraitor-parallel-lane-orchestration/SKILL.mdgit clone --depth 1 https://github.com/jerseycheese/NarraitorWrote 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/jerseycheese/narraitor/narraitor-parallel-lane-orchestration)<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-parallel-lane-orchestration"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-parallel-lane-orchestration/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/jerseycheese/narraitor/narraitor-parallel-lane-orchestration"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-parallel-lane-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.02452 |
| Opus 5 | $0.00065 | $0.01226 |
| Sonnet 5 | $0.00026 | $0.00490 |
| Haiku 4.5 | $0.00013 | $0.00245 |
Grade A, and why
narraitor-parallel-lane-orchestration 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 12d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel lane orchestration (Fable orchestrator, tiered lane agents)
1. What this is
One Fable-model session acts as orchestrator. It picks N issues off the backlog, pre-builds a
git worktree per issue, and spawns one Agent-tool subagent per lane — each lane's model chosen
from that issue's model-power:* label, so cheap work runs cheap. The orchestrator never
implements; it selects, partitions, dispatches, unblocks, and reports.
The mechanism that works here is the in-harness Agent tool, not claude -p children
(host-held OAuth 401s) and not a paste-block of terminal commands.
2. When to use
- "Work the next N most important issues in parallel."
- A backlog push where serial execution would waste hours of wall clock.
- Any time a batch is big enough that batch selection is itself a real decision.
Do not use for a single issue (ship-issue / tdd-implement are cheaper), or when the batch
would all touch the same file (see collision rules — that batch is serial by nature).
3. Model tiering
model-power:* is the delegation axis (complexity:* is time/scope, not reasoning difficulty).
Definitions live in .github/labels.md.
| Label | Lane model |
|---|---|
model-power:light |
haiku |
model-power:standard |
sonnet |
model-power:advanced |
opus |
model-power:frontier |
keep out of the batch, or run it in the orchestrator session |
An unlabeled issue is not automatically standard — read the body and assign a tier, saying so.
The labels were applied in a single retroactive pass, so treat a tier that fights the body as
wrong and score the body.
4. Batch selection
Run the prioritize-issues skill for the ranking, then subtract everything that cannot safely
run right now. That skill is user-level, not committed here — where it isn't available (a fresh
clone, a cloud session), the repo ships .claude/agents/issue-prioritizer.md, which does the
same ranking job:
- Already in motion. Any issue with an open PR, or an existing worktree/branch matching its number. A pre-existing worktree is not proof of abandonment — ask before touching it.
- Explicitly held. A draft PR on a HOLD, an issue whose body says it lands with or after another PR, an issue waiting on a spending or design decision.
- Collision. Predict each candidate's file set. Intersect the sets pairwise. Overlapping
candidates either get one named sole owner for the shared file (the other is told in writing
not to touch it) or one of them drops out of the batch. Shared prompt templates
(
sceneTemplate.tsand friends) and shared CSS are the repeat offenders.
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.
- 12d ago First seen · 175 lines · 130 tokens per session scan A f97d6752e2d9
narraitor-parallel-lane-orchestration is a skill published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 2,452 once invoked, about $0.0006 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…