project-recap

A command for generating a visual project recap: a self-contained HTML page that summarises a project for someone returning after time away.

In plain words
What is it for?
Use it to document project structure, current git state, recent commits, TODOs, blockers, and suggested next steps, with a compact mode available when requested.
Why use it?
It gathers key project files, code areas, recent changes, and outstanding work so a developer can rebuild their understanding quickly.

Command

Install

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.

agentmods
npx agentmods add commands/nicobailon/visual-explainer/project-recap
Clone the repo
git clone --depth 1 https://github.com/nicobailon/visual-explainer
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00440
Opus 5 $0.00006 $0.00220
Sonnet 5 $0.00002 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash ace23387b95c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 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.

plugins/visual-explainer/commands/project-recap.md · 34 lines

What it actually says

Load the visual-explainer skill and generate a self-contained HTML project recap.

Quick mode

Only use quick mode when $@ contains the literal --quick flag. Remove the flag before interpreting any recap arguments. Complete the same project research and verification below, then read ./quick/README.md and ./quick/schema.json and express the recap as a compact spec. In Pi, call visual_explainer with action: "render_quick". In other harnesses, run the local ./quick/render.mjs fallback. If the recap does not fit the schema, validation fails, or rendering errors, generate complete HTML and use the normal render flow. Without --quick, preserve full HTML behavior.

Data gathering before HTML

Read project identity files (README, changelog, package/build files), top-level tree, current git status, recent commits, unmerged/stale branches, TODO/FIXME in recent files, progress/todo memory if present, and key entry points/source files. Focus on what a returning developer needs to rebuild the mental model.

Verify before generating

Cite command output or file:line evidence for project state, module/function/type names, recent activity, current blockers, and next-step claims. Do not fabricate momentum or rationale.

Required page sections

  1. Project identity: what this repo is, stack, entry points.
  2. Architecture snapshot: Mermaid or hybrid diagram of current conceptual modules.
  3. Recent activity: grouped narrative, not raw log.
  4. Current state: uncommitted work, branches, TODOs, known blockers.
  5. Mental model map: key modules, data flow, command/test/deploy paths.
  6. Risks and cognitive debt: hotspots and gotchas.
  7. Useful commands and files.
  8. Likely next steps, based only on evidence.

Use responsive nav. Use compact reference tables for file maps and commands. Follow the skill’s Mermaid, overflow, and delivery rules.

Write to ~/.agent/diagrams/ and open in browser.

Changes

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.

  1. 2d ago First seen · 34 lines · 12 tokens per session scan A ace23387b95c

Subscribe to this mod's changes

project-recap is a command published in the GitHub repository nicobailon/visual-explainer (9,621 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 440 once invoked, about $0.0001 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 2026-08-30.