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 agentmods add skills/tslateman/duet/visual-recapnpx skills add tslateman/duet --skill visual-recapgit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/visual-recap)<a href="https://agentmods.dev/skills/tslateman/duet/visual-recap"><img src="https://agentmods.dev/badge/skills/tslateman/duet/visual-recap.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01649 |
| Opus 5 | $0.00035 | $0.00825 |
| Sonnet 5 | $0.00014 | $0.00330 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
visual-recap 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 4d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Recap
A recap is a structured summary built from a diff, not toward one. Forward planning describes the change you are about to make; a recap describes the change that was just made, one altitude above line-by-line review. A reviewer scans the shape of the change, UI delta, schema delta, contract delta, file footprint before spending attention on the literal lines.
Adapted from BuilderIO/skills visual-recap. The discipline is theirs; the
output targets are yours. There is no hosted plan renderer here, so author plain
artifacts.
When To Use
Build a recap when a PR or commit is large, multi-file, or touches schema, API contracts, or architecture, and a reviewer benefits from seeing the change mapped to structure before reading the diff. Skip it for small, single-file, or obvious diffs, a recap is review overhead, and a tiny change reviews faster as plain diff. Never pad a trivial diff into a recap.
Default scope is the whole work unit: original implementation plus later fixes, tests, and follow-ups, not only the most recent commit. Use the diff plus context to separate work-unit changes from unrelated pre-existing edits, and exclude the unrelated ones. State the assumption if scope is ambiguous.
The Grounding Rule
Structured blocks are true by construction only when derived mechanically from the actual changed lines. Build the file map, schema table, API table, and diffs from the real diff, real paths, real fields, real method and path, real before/after text. Never infer, round, or invent them. The model writes only the prose: the "why", the narrative, the risk read. A confidently wrong recap is dangerous, because a reviewer who trusts the summary skips the line the summary got wrong. When the diff does not contain a fact, leave it out. Mark anything inferred rather than extracted as inferred.
Canonical Shape And Budgets
A strong recap follows one skeleton, top to bottom. Drop any section the diff does not touch.
- UI headline, before/after wireframe or screenshot, first, when the diff changed rendered UI.
- Outcome narrative, 1-3 paragraphs: what changed and why, the key decisions visible in the diff, the risk a reviewer should weigh. The only place you write freely.
- Schema / contract changes, a
data-modeltable for migrations, an endpoint table for API/route changes. - Changed-file map, every changed file with an added/removed/modified/ renamed flag and a one-line note, so the footprint reads at a glance.
- Key changes, focused diffs of the 3-8 load-bearing files, each under a one-line summary of what it changes and why.
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.
- 4d ago First seen · 133 lines · 70 tokens per session scan A 52514314cd3f
visual-recap is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 1,649 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.