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 commands/nicobailon/visual-explainer/project-recapgit clone --depth 1 https://github.com/nicobailon/visual-explainerWhat 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 | $0.00012 | $0.00440 |
| Opus 5 | $0.00006 | $0.00220 |
| Sonnet 5 | $0.00002 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
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.
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
- Project identity: what this repo is, stack, entry points.
- Architecture snapshot: Mermaid or hybrid diagram of current conceptual modules.
- Recent activity: grouped narrative, not raw log.
- Current state: uncommitted work, branches, TODOs, known blockers.
- Mental model map: key modules, data flow, command/test/deploy paths.
- Risks and cognitive debt: hotspots and gotchas.
- Useful commands and files.
- 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.
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 First seen · 34 lines · 12 tokens per session scan A ace23387b95c
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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
ado-pull
Pull latest changes from Azure DevOps (like git pull). Supports increment, project, or full living docs sync.
issue-amend
Re-snapshot the active issue's scope from the spec, clear verified and reviewed receipts, and record the change as a permanent amendment.
dispatch-worker
Run one in-session-agent Worker tick (RFC-0041 §4.3.1).
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.