Borrowing it
Nothing to install: this file belongs to kuhumcst/DanNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kuhumcst/DanNet/master/.claude/skills/project-summary/SKILL.mdgit clone --depth 1 https://github.com/kuhumcst/DanNetWrote 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/kuhumcst/dannet/project-summary)<a href="https://agentmods.dev/skills/kuhumcst/dannet/project-summary"><img src="https://agentmods.dev/badge/skills/kuhumcst/dannet/project-summary.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.00555 |
| Opus 5 | $0.00034 | $0.00278 |
| Sonnet 5 | $0.00014 | $0.00111 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
project-summary 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 8d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining PROJECT_SUMMARY.md
PROJECT_SUMMARY.md is the codebase map that AI sessions (and humans) rely on. It was originally generated and maintained by clojure-mcp's update prompts; those don't run under Claude Code, so keeping it accurate is now part of finishing substantial work.
When to update
After completing work that changes what the file claims: new or removed namespaces, new dependencies, changed architecture or data flow, new web endpoints or UI components, new MCP server tools, changed build/test/dev workflow, new bootstrap datasets. If a change only alters the inside of existing functions, the summary is not affected — leave it alone.
How to update
- Surgical edits only: touch the sections the change affects, preserve the overall heading structure and tone. Other tooling references section names (e.g. the browser-repl-debug skill grew out of "Browser REPL Debugging (shadow-cljs)"), so don't rename headings casually.
- Verify claims against the actual code before writing them — read the namespace, check deps.edn, or probe via the REPL. Don't describe the change from memory of what you intended; describe what landed.
- The file's register is factual and compact: what exists, where it lives, how it connects. No selling, no progress narrative, no changelog entries — git history covers history.
- Prefer removal over accretion: when a section describes something that no longer exists, delete it rather than layering corrections ("nothing left to take away").
- Keep it a summary. If a section needs deep detail, it likely belongs in doc/ with a pointer here.
Structure to preserve
Top-level sections as of August 2026: Overview · Key Architecture Components (one subsection per subsystem, with namespace names in the headings) · File Structure · Dependencies · Development Workflow (Setup, REPL Development, Frontend Development, Browser REPL Debugging, Running Tests, Building Releases) · Conventions and Patterns · Extension Points · Integration Examples · Performance Considerations · Related Documentation · Special Instructions for AI/LLM Assistants.
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.
- 8d ago First seen · 51 lines · 69 tokens per session scan A 1a3dd4746aa9
project-summary is a skill published in the GitHub repository kuhumcst/DanNet (29 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 555 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 2026-08-30.
Other skills, from other repositories
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
review
Structured PR review for pygraphistry. Input: PR number/branch (default current branch PR). Output: findings and convergence artifacts under plans/ /. Method: multi-wave, evidence-first review across spec, correctness, tests, security, code quality, DRY, concurrency, performance, architecture, operability, and…
test-amplification
Methodical bug-driven test amplification for pygraphistry features. Use when hardening a feature area via user-workflow exploration, 5-Whys retrospectives, bug-taxonomy derivation, concrete test planning, implementation, and safety-gated validation.
plan
OPT-IN file-based planning for multi-session tasks. Only use when user explicitly requests it or work spans multiple sessions. For single-session work, prefer your platform's native planning features.
deck-graphify-dark
A dark slide-deck template for AI tools, developer tools, and knowledge graphs, using gradients, floating blurred shapes, graph diagrams, code styling, and glass-like cards.
blueprint-graphs
Add, connect, and configure nodes in Blueprint event graphs and function graphs — function-call/event/branch/timer/custom-event/delegate nodes, Standard Macro nodes (ForEachLoop/ForLoop/WhileLoop/DoOnce/Gate/IsValid/FlipFlop via addmacroinstancenode), macro-graph creation, pin wiring, node layout, arrays, comment…