Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/project-context-loaderWrote 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/nguyenthienthanh/aura-frog/project-context-loader)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/project-context-loader"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/project-context-loader/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/nguyenthienthanh/aura-frog/project-context-loader"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/project-context-loader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 102 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00022 | $0.00829 |
| Opus 5.5 | $0.00009 | $0.00332 |
| Sonnet 5.5 | $0.00004 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
project-context-loader 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Project Context Loader
Load project conventions and generate session context on demand.
When to Use
Before: /run, code generation, refactoring, test writing.
Skip: Simple questions (no code), when session-context.toon already loaded.
Loading Process
0. Host-Project Documents First (authoritative)
Before any cache or generated context, read the host project's own documentation — it is written by humans and overrides anything this skill infers:
| File | Priority |
|---|---|
CLAUDE.md (root) and/or .claude/CLAUDE.md |
Highest — project instructions (per rules/workflow/priority-hierarchy.md) |
README.md (root) |
High — purpose, setup, run commands, structure |
CONTRIBUTING.md (if present) |
Conventions for changes |
Read them fully on first load of a session (they are usually short). On conflict between these and generated context below, the host project's docs win — refresh the cache instead of trusting it.
1. Check Cache
If .claude/session-context.toon exists and is recent (< 1 hour), use it.
2. Generate (If Missing)
Scan codebase for: file naming, import style, export pattern, error handling, testing framework, styling approach. Write to .claude/session-context.toon.
3. Load Project Config
From .claude/project-contexts/[project]/:
| File | When |
|---|---|
project-config.yaml |
Always |
conventions.md |
Always |
rules.md |
Always |
repo-map.md |
First task |
file-registry.yaml |
When modifying code |
architecture.md |
Architecture decisions |
4. Smart Loading
loading_strategy[4]{scenario,files_to_load}:
Simple question,session-context.toon only
Bug fix / small change,"session-context.toon + conventions.md + file-registry.yaml"
New feature / refactor,All 7 files
Architecture decision,"session-context.toon + architecture.md + repo-map.md"
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 Changed · +12 lines f46764735b3e
- 1mo ago First seen · 93 lines · 22 tokens per session scan A 5aa8a57f8cc3
project-context-loader is a skill published in the GitHub repository nguyenthienthanh/aura-frog (25 stars, last pushed 8d ago), licensed MIT. It adds 22 tokens to every session and 829 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 2026-09-03.
Other skills, from other repositories
create_note
Capture findings or context as a persistent note in the thoughts system.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-design
Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval.