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 OutlineDriven/outline-driven-development --skill backloggit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/backlog)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/backlog"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/backlog.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00881 |
| Opus 5 | $0.00017 | $0.00441 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
backlog 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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to park an undecided idea without representing it as decided or active work. |
| Authority | Reversible local: writes only one backlog entry file; rollback is deleting or reverting that file. No remote mutation. No VCS commit or credential use. |
| Side effect | One backlog entry as a reversible local state change with recorded evidence. |
| Done | The idea is parked in the backlog and ready to be promoted when it meets the readiness threshold. |
Inputs
- Idea statement (required): one or two sentences naming the idea and the problem it would address.
- Undecided reason (required): the specific missing input that blocks a decision now: an unverified assumption, absent evidence, an open question, or a competing alternative.
- Readiness threshold (required): the concrete, falsifiable condition that, when met, would make the idea promotable (a measurement, a resolved question, or a confirmed constraint that yields a yes/no).
- Existing evidence (optional): links, measurements, or notes already in hand that bear on the idea.
- Backlog location (optional): path to the backlog file or directory; default is a
backlog.mdfile in the current workspace.
Procedure
- Validate the inputs: confirm the idea statement is a single coherent proposal, the undecided reason names a concrete missing input, and the readiness threshold is falsifiable. A human or tool must be able to test it and get a yes/no result. Done when: all three required inputs are validated as coherent, concrete, and falsifiable.
- Bound scope: this skill only parks the idea. Do not evaluate, rank, or promote it. Do not create tasks, requirements, or tickets. Done when: scope is bounded to parking only with no evaluation, ranking, or promotion.
- Locate or create the backlog store. If a backlog file exists, append to it; otherwise create one with a header marking it as undecided-parking only. Done when: the backlog store is located or created.
- Write one entry with the idea statement, undecided reason, readiness threshold, any supplied evidence, timestamp, and a stable identifier. Derive the identifier from the idea statement as a kebab-case slug (lowercase words joined by hyphens, with non-alphanumerics dropped); on collision with an existing identifier, append
-2,-3, and so on. Mark the entry statusparked. Done when: the entry is written with all fields and markedparked. - Record the entry as a reversible local state change: the file write is the only mutation. No commit, push, or remote call occurs. Done when: the entry is recorded as the only mutation with no commit, push, or remote call.
- Confirm the done predicate: the entry exists, is marked
parked, and carries its readiness threshold so a later promotion step can test it. Done when: the entry is confirmed present, parked, and threshold-carrying.
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.
- 2d ago Changed · -15 tokens per session 8302836c64cc
- 4d ago First seen · 42 lines · 49 tokens per session scan A 75d7e5a74265
backlog is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 881 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 2026-09-03.
Other skills, from other repositories
drift-detect
Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.
github-backlog-triage
Use when the user invokes backlog triage for a GitHub repo's open issues and PRs. Not for proactive triage, non-GitHub trackers, or single bug issues: use github-bug-report-triage.
setup-repo-skills
Use when the user wants one-time repository setup for tracker, triage labels, and domain conventions. Not for ongoing triage, issue creation, or multi-repo setup.
git-history-analysis
Use when the user asks about recent engineering work, what the team is working on, planning or roadmap material, or an explicitly requested Slack summary. Not for remote or irreversible changes.
graph-backbone
Use when defining, revising, or gate-replanning the project structural backbone in project-root graph.yaml; produces a validated approved revision preserving immutable topology and additive metadata. Not for remote, credential, publish, deploy, or irreversible changes.
wontfix
Use when the user wants to elicit refused directions, generalize them, and close matching tracker items as not planned. Not for duplicates, spam, or items closed as completed or obsolete.