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 ychampion/cskill-agents --skill project-root-scoped-local-skill-loadinggit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/project-root-scoped-local-skill-loading)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/project-root-scoped-local-skill-loading"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/project-root-scoped-local-skill-loading/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/ychampion/cskill-agents/project-root-scoped-local-skill-loading"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/project-root-scoped-local-skill-loading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.00404 |
| Opus 5.5 | $0.00012 | $0.00162 |
| Sonnet 5.5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
project-root-scoped-local-skill-loading 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.
What it actually says
SKILL: Project-Root Scoped Local Skill Loading
Domain: skill-loading Trigger: Apply when local commands or skills must be discovered from the current workspace and later merged with other registries such as MCP or bundled sources. Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
Resolve the canonical project scope before loading any local command or skill surface. Feed that stable root into the local loader so discovery is anchored to the workspace boundary rather than to whatever transient working directory or caller context happened to invoke the pipeline. Once the local set is loaded from that scoped root, it can be safely merged with remote or external sources without mixing project-relative lookup with cross-source combination logic.
Key Rules
- Determine a stable project root first and pass that explicit scope into the local skill loader.
- Keep local loading separate from later merge logic so source-specific discovery remains easy to reason about.
- Treat the project root as the authoritative boundary for local skills, not the caller's incidental cwd.
- Load the local project surface before combining it with external registries so downstream dedupe and formatting see one correctly scoped local set.
Example Application
If a coding agent builds a skill listing from both the current repository and connected MCP servers, resolve the repository root first, load local skills relative to that root, then merge the resulting local commands with the MCP skills. This prevents a subdirectory invocation from silently narrowing the local skill surface.
Anti-Patterns (What NOT to do)
- Do not call the local loader against an arbitrary runtime cwd when the real scope should be the project root.
- Do not intertwine project-root resolution with multi-source merging; local scoping should be correct before any external source is introduced.
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 · 28 lines · 31 tokens per session scan A eec9ffa4286f
project-root-scoped-local-skill-loading is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 404 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
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.