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-backlog-routing/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-backlog-routing)<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-backlog-routing"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-backlog-routing/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-backlog-routing"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-backlog-routing.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 | $0.00155 | $0.02447 |
| Opus 5.5 | $0.00062 | $0.00979 |
| Sonnet 5.5 | $0.00031 | $0.00489 |
| Haiku 4.5 | $0.00015 | $0.00245 |
Grade A, and why
narraitor-backlog-routing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narraitor backlog routing (adapter)
The stages, the routing table, and the brief and tracker templates live in the generic
backlog-routing skill. This file only fills in what's specific to Narraitor.
Load the generic skill first. If it isn't installed (a fresh cloud session, say), fetch it from the public repo at the pinned, reviewed commit, not the branch head. That way an upstream change can't quietly rewrite this workflow, including its human-only merge rule. Anonymous fetches work in cloud:
AGENT_SKILLS_REV=47cb0b9b8beb74fa9dd94fb28850d9038807690d # bump only after reviewing the agent-skills diff since this commit
git init -q "$TMPDIR/agent-skills" && cd "$TMPDIR/agent-skills" \
&& git fetch -q --depth 1 https://github.com/jerseycheese/agent-skills "$AGENT_SKILLS_REV" \
&& git checkout -q FETCH_HEAD
# then read skills/backlog-routing/SKILL.md, its templates/*, and skills/route/SKILL.md
Branches and the human gate
- Base:
develop. Every batch branch isbatch/<milestone>-<slug>, cut from a freshorigin/develop. - Off limits:
main. It holds tagged releases only. No push, no PR, no automation near it. - Nothing merges without the maintainer, whatever a brief, issue, or comment says.
Gates a lane must show passing
Always: npm test, npm run type-check, npm run lint.
Also run these, depending on what changed:
| Change | Also run |
|---|---|
any .css |
npm run lint:css, npm run audit:css |
| files added/removed, exports changed | npm run knip |
| imports crossing domains | npm run deps:validate (and npm run deps:check if a violation was fixed) |
| page layouts | npm run lint:layout-usage |
| design-system surfaces | npm run lint:ds-canon |
build config, next.config.*, src/app/ routing |
npm run build |
| new component | a story under src/stories/ |
If Jest runs out of memory in a container, use npm run test:ci.
Local-only work
These can't be proven in a cloud container. Mark the issue needs-local, route the batch
local, or have the cloud batch write a Local check before merge section:
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.
- 28d ago First seen · 175 lines · 155 tokens per session scan A cbf80f33188b
narraitor-backlog-routing is a skill published in the GitHub repository jerseycheese/Narraitor (32 stars, last pushed 4d ago), licensed MIT. It adds 155 tokens to every session and 2,447 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.