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 HashLips/agent-skills --skill project-graphgit clone --depth 1 https://github.com/HashLips/agent-skillsWrote 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/hashlips/agent-skills/project-graph)<a href="https://agentmods.dev/skills/hashlips/agent-skills/project-graph"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/project-graph/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/hashlips/agent-skills/project-graph"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/project-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 16 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00093 | $0.02080 |
| Opus 5.5 | $0.00037 | $0.00832 |
| Sonnet 5.5 | $0.00019 | $0.00416 |
| Haiku 4.5 | $0.00009 | $0.00208 |
Grade A, and why
project-graph 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 1mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Graph
Core Rules
- Run
scripts/generate-graph.pywithpython3; it has no third-party dependencies. The CLI is a thin wrapper over thescripts/project_graph/package (discovery, parsing, flows, knowledge, build, render). - Privacy first: the script never opens or includes dotfiles or dot-folders (
.env*,.git/,.github/,.vscode/, and so on); the only dotfile it reads is.gitignore, and only to learn which paths to ignore. Never weaken this rule. - The script respects
.gitignoreautomatically (viagit ls-files, with a manual fallback), sonode_modules, build output, and machine-local files never enter the graph. - Output is a single self-contained file,
project-graph.html, written to the project root by default. It does not embed absolute machine paths; Go to file resolves the project root from where each user opens the HTML (with an optional per-browser override in the Config tab). - Flows are first-class: routes, API handlers, and entry files are auto-detected; important business flows (for example "send OTP") should be defined in a
project-graph.flows.jsonmanifest so users can click a flow and see every file it touches. - The graph is a living artifact:
project-graph.knowledge.jsonat the project root holds AI-authored understanding (overview, technologies, services, flow insights and diagrams, file notes) and is merged into every regeneration. Writing the JSON alone does not update the dashboard — you must always regenerateproject-graph.htmlafterward and verify the merge (see Knowledge update loop below). - Knowledge grows incrementally and context-cheaply: investigate only what the question needs (manifests first, then entry files), write short summaries, and always merge into the existing knowledge file - never rewrite it wholesale and never bulk-analyze the project.
- When regenerating the graph, if
project-graph.knowledge.jsoncontains flow diagrams, re-verify each against its entry point (and only files referenced in the diagram) before finishing; update any stale insight or diagram, leave accurate ones unchanged. See references/knowledge.md diagram refresh rules. - Always verify the run via the exit code and the
PROJECT_GRAPH_RESULTline; never read the generated HTML wholesale to check it. - Works on any project (API, client app, monorepo, docs repo) on any machine with Python 3.8+; never assume a specific framework, repo layout, or skill install path. See references/portability.md.
- The skill install folder and the mapped project are independent — resolve
generate-graph.pyper references/portability.md; never hardcode one developer's paths. - Do not commit
project-graph.htmlunless the user asks for it.
What ships with it
23 files 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.
- .gitignore 23 B
- references/dashboard-guide.md 5.9 KB
- references/flows.md 2.2 KB
- references/knowledge.md 8.0 KB
- references/portability.md 3.7 KB
- references/script-usage.md 6.0 KB
- references/self-healing.md 4.7 KB
- scripts/generate-graph.py 1.3 KB runs code
- scripts/project_graph/__init__.py 270 B runs code
- scripts/project_graph/build.py 6.6 KB runs code
- scripts/project_graph/categorize.py 1.1 KB runs code
- scripts/project_graph/cli.py 4.5 KB runs code
- scripts/project_graph/constants.py 3.7 KB runs code
- scripts/project_graph/discovery.py 3.0 KB runs code
- scripts/project_graph/editor_detect.py 1.4 KB runs code
- scripts/project_graph/flows.py 5.8 KB runs code
- scripts/project_graph/knowledge.py 6.1 KB runs code
- scripts/project_graph/parsing.py 1.6 KB runs code
- scripts/project_graph/refs.py 4.7 KB runs code
- scripts/project_graph/render.py 693 B runs code
- scripts/project_graph/resolver.py 7.7 KB runs code
- scripts/project_graph/template.html 87 KB
- scripts/project_graph/verify.py 2.3 KB runs code
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.
- 1mo ago First seen · 102 lines · 93 tokens per session scan A c494d32290a2
project-graph is a skill published in the GitHub repository HashLips/agent-skills (28 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 2,080 once invoked, about $0.0004 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.