Borrowing it
Nothing to install: this file belongs to thomwebb/gac. 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/thomwebb/gac/main/.skills/project-nav/SKILL.mdgit clone --depth 1 https://github.com/thomwebb/gacWrote 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/thomwebb/gac/project-nav)<a href="https://agentmods.dev/skills/thomwebb/gac/project-nav"><img src="https://agentmods.dev/badge/skills/thomwebb/gac/project-nav/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/thomwebb/gac/project-nav"><img src="https://agentmods.dev/badge/skills/thomwebb/gac/project-nav.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 93 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 95 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00033 | $0.01109 |
| Opus 5.5 | $0.00013 | $0.00444 |
| Sonnet 5.5 | $0.00007 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
project-nav 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Navigation
When to Use
- Finding where specific code lives
- Understanding project structure
- Locating configuration files
- Looking for where to add new features
Structure (106 source files)
gac/
src/gac/
cli.py # Click CLI entrypoint
main.py # Commit workflow orchestration
ai.py / ai_utils.py # AI provider integration + retry logic
prompt.py / prompt_builder.py # Dual-prompt system
git.py # Git operations
security.py # Secret detection
config.py # Config loading (GACConfig TypedDict)
errors.py # Exception hierarchy (GACError base)
preprocess.py / postprocess.py # Diff preprocessing / message cleanup
diff_scoring.py # Diff relevance scoring
providers/ # 35 provider implementations
__init__.py # PROVIDER_REGISTRY
base.py # BaseConfiguredProvider, OpenAICompatibleProvider,
# AnthropicCompatibleProvider, GenericHTTPProvider
error_handler.py # @handle_provider_errors decorator
protocol.py # ProviderProtocol
registry.py # register_provider()
openai.py, anthropic.py, gemini.py, ...
oauth/ # OAuth authentication
base.py # Base OAuth flow (19KB)
chatgpt.py # ChatGPT OAuth
claude_code.py # Claude Code OAuth
copilot.py # GitHub Copilot OAuth
token_store.py # Token storage (~/.gac/oauth/)
stats/ # Statistics tracking
store.py # Stats file read/write
recorder.py # Usage recording
commands.py # Stats CLI commands
charts.py # Chart generation
summary.py # Summary formatting
migration.py # Legacy migration
mcp/ # MCP server
server.py # MCP server implementation (22KB)
server_utils.py # Server utilities
models.py # MCP data models
constants/ # Constants package
defaults.py # EnvDefaults, etc.
commit.py # Commit format constants
file_patterns.py # Secret detection patterns
languages.py # Language code mappings
grouped_commit_*.py # Grouped commit workflow (5 files)
*_cli.py # Subcommand CLIs (config, init, diff, model, etc.)
workflow_context.py # WorkflowContext dataclass
tests/ # 151 test files mirroring src/
docs/ # Documentation (16 languages)
scripts/ # Automation helpers
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.
- 2mo ago First seen · 117 lines · 33 tokens per session scan A 6e456eb84797
project-nav is a skill published in the GitHub repository thomwebb/gac (318 stars, last pushed 18d ago), licensed MIT. It adds 33 tokens to every session and 1,109 once invoked, about $0.0001 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.
project-nav compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project-navthomwebb/gac | Skill | 318 | 18d ago | MIT | A | 33 | Claude Code, Codex |
| new-projectsergenes/mini_agent | Skill | 37 | 2mo ago | none | A | 51 | Claude Code, Codex |
| deployment-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 41 | Claude Code, Kiro |
| mem0-test-integrationmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 207 | Claude Code, Codex |
| resolve-handoffomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 23 | Claude Code, Codex |
| otto-pr-review-loopomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 17 | Claude Code, Codex |
| baby-sitlangchain-ai/open-swe | Skill | 11k | yesterday | MIT | A | 30 | Claude Code, Codex |