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 convergegit 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/converge)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/converge"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/converge/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/converge"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/converge.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 | $0.00038 | $0.00713 |
| Opus 5 | $0.00019 | $0.00357 |
| Sonnet 5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
converge 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Converge
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to collapse an open decision field to one decision and record its rationale. |
| Authority | Reversible local: writes only one named local decision record file; rollback is deleting or reverting that file. No remote mutation. |
| Side effect | A decision and rationale written to one local decision record file; the open field is marked collapsed. |
| Done | The decision field is collapsed to one decision with a distinguishing rationale recorded in the local decision file. |
Inputs
- The open decision field: the set of considered options, recorded human opinions, agent doubts, and obvious assumptions. Required.
- The human's chosen option. Required; if not supplied, prompt the human to select one.
- The decision record path. Optional; defaults to
docs/decisions/YYYYMMDD-decision.mdwhere YYYYMMDD is today's date.
Decision record format
# Decision: <one-line summary>
Date: YYYY-MM-DD
## Chosen option
<the selected option>
## Rationale
<why this option won>
## Rejected options
- <option>: <why it was rejected>
- <option>: <why it was rejected>
Procedure
- Read the open decision field and enumerate every considered option, recorded human opinion, agent doubt, and obvious assumption. If no field exists, stop: there is nothing to collapse. Done when: every option, opinion, doubt, and assumption in the field is enumerated, or the absence of a field is reported.
- If the human's chosen option was not supplied, prompt the human to select one option from the field. Do not select on the human's behalf. Done when: the human has selected one option from the field.
- State the rationale that distinguishes the chosen option from each rejected option: why it won and why each other did not. If the rationale holds equally for a rejected option, ask the human to sharpen it before recording. Done when: a distinguishing rationale is stated for the chosen option against every rejected option.
- Write the chosen option and its distinguishing rationale to the decision record file at the determined path using the format above. Create the parent directory if needed. Mark the field collapsed. Done when: exactly one decision is recorded with rationale and the field is marked collapsed.
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 d9bb13601689
- 4d ago First seen · 62 lines · 38 tokens per session scan A ab1faf43d0c7
converge is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 713 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.