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 portable-skill-loader-progressive-disclosuregit 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/portable-skill-loader-progressive-disclosure)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/portable-skill-loader-progressive-disclosure"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/portable-skill-loader-progressive-disclosure/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/portable-skill-loader-progressive-disclosure"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/portable-skill-loader-progressive-disclosure.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 | $0.00029 | $0.00366 |
| Opus 5 | $0.00015 | $0.00183 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
portable-skill-loader-progressive-disclosure 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.
What it actually says
SKILL: Portable Skill Loader Progressive Disclosure
Domain: skill-loading Trigger: Use when an agent must scan thousands of skills but only load detailed prompts for the handful that are actually invoked. Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
Separate discovery from loading. During startup, scan only lightweight metadata such as the skill name, summary, trigger text, and file location to build a searchable index. Load the full instruction body only after the agent actually selects that skill, and cache the resolved metadata and file identities so repeated lookups stay cheap. Deduplicate by canonical path, and skip invalid or ignored skill directories without failing the whole scan.
Key Rules
- Read only lightweight metadata during discovery; defer the full skill body until invocation time.
- Resolve canonical paths so duplicate folders, symlinks, and mirrored mounts do not appear as separate skills.
- Treat malformed frontmatter or missing files as warnings to skip, not as fatal startup errors.
- Cache discovery results per source and invalidate them only when the relevant roots or settings change.
Example Application
When building a CLI skill browser for a large monorepo, index every skill folder using only summary metadata at startup, then load the full instructions only for the skills the user or model actually opens.
Anti-Patterns (What NOT to do)
- Don’t eagerly read every
SKILL.mdfile during startup; that blocks discovery and may exceed token budgets. - Don’t treat invalid frontmatter as fatal—skip the skill instead of crashing.
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 · 28 lines · 29 tokens per session scan A 8da0ba9c0463
portable-skill-loader-progressive-disclosure is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 366 once invoked, about $0.0001 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 2026-09-03.
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.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.