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 developer-experience-reviewgit 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/developer-experience-review)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/developer-experience-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/developer-experience-review/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/developer-experience-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/developer-experience-review.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 | $0.00036 | $0.01138 |
| Opus 5 | $0.00018 | $0.00569 |
| Sonnet 5 | $0.00007 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
developer-experience-review 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 3d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer experience review
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user runs /developer-experience-review to dogfood a developer-facing product or workflow |
| Authority | Reversible local: writes only a review log and an optional plan-review section; rollback is undo. No remote mutation. Browser and CLI interactions are reads that change no remote, credential, paid, published, or deployed state. |
| Side effect | A review log and an optional plan-review section under the working directory |
| Done | An evidence-backed eight-dimension scorecard reports measured time to hello world and prioritized DX fixes |
Inputs
- The product or workflow to dogfood, named by the user (URL, repo path, CLI command, or workflow description). Required.
- One or more benchmark products to score against, named by the user. Optional; when omitted, score the product alone and mark each dimension as absolute rather than comparative.
- A working directory writable for the review log. Defaults to the current directory.
Procedure
-
Record the target product, any benchmark products, and the current wall-clock start time in the review log. Done when: the review log holds the target, benchmarks, and start time.
-
Dogfood the target end to end through the live browser and CLI exactly as a new developer would: install or open it, follow the documented first path, and reach the first meaningful output ("hello world"). Do not skip steps the documentation does not name; do not use private knowledge to bypass friction. Done when: the first meaningful output is reached or the run is blocked at a named step.
-
Measure elapsed wall-clock time from the start recorded in step 1 to the first meaningful output. Record the value and every blocking step that extended it. Done when: the elapsed time and blocking steps are recorded.
-
Repeat steps 2-3 for each benchmark product, using the same first-meaningful-output definition, and record each measured time. Done when: every benchmark is dogfooded with its time recorded, or dropped with a reason.
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.
- 3d ago Changed · -12 tokens per session 8d4916dde7d9
- 5d ago First seen · 60 lines · 48 tokens per session scan A c7b8b182952a
developer-experience-review is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,138 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.
snippet-image-rendering
Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.