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 dedup-skillsgit 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/dedup-skills)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/dedup-skills"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/dedup-skills/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/outlinedriven/outline-driven-development/dedup-skills"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/dedup-skills.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 | $0.00048 | $0.01317 |
| Opus 5 | $0.00024 | $0.00659 |
| Sonnet 5 | $0.00010 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
dedup-skills 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dedup skills
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to deduplicate a skill tree, fold overlapping skills, or cut the skill count. |
| Authority | Human-gated: requires explicit human invocation; the analyze phase writes only the fold ledger; the dedup phase runs only on an explicit user command naming approved families and then writes skill directories, descriptions, the attribution file, the changelog, and generated surfaces, one commit per family; rollback is git revert of that commit. No remote mutation. |
| Side effect | A fold ledger, then per approved family: the survivor absorbs the members' unique steps, the members are deleted, pointers are rewritten, attribution and changelog are updated, and generated surfaces are re-rendered. |
| Done | Every family in the ledger carries a decision; every approved family is folded in its own commit; the checker reports no dangling pointer; the removed count and the remaining count are measured, not projected. |
Inputs
- Target tree path (default
plugins/). Every<plugin>/skills/<slug>/SKILL.mdunder it is a skill. - The tree's attribution file (
licenses/NOTICEor equivalent), read in full before scanning. A license-covered skill is a fold candidate like any other; the attribution follows the text. - Reduction floor (optional): a count or percent the fold must clear. The floor never loosens the fold criteria; a shortfall is reported at the gate.
Fold criteria
Two skills belong to one family when a user asking for one would accept the other's procedure with a parameter changed. Three evidence sets, in priority order:
- Pointer neighbors: descriptions that route to each other through
Not for <x>: use <y>. Adjacency is evidence, not proof; a component that chains distinct jobs (implement, test, ticket) is several families or none. - Parameter siblings: slugs that differ by one axis (
from-<seat>-perspective,watch-<mode>,culture-<situation>), whose procedures share every step except the parameterized one. - Mode siblings: skills whose descriptions differ only by a mode word (
exhaustive,batch,interview) over one procedure.
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 · +18 lines · -2 tokens per session 07bf28f5ceeb
- 5d ago First seen · 46 lines · 50 tokens per session scan A 995b91e8fcf0
dedup-skills is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,317 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
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.