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 dynamic-skill-insertion-before-builtinsgit 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/dynamic-skill-insertion-before-builtins)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/dynamic-skill-insertion-before-builtins"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/dynamic-skill-insertion-before-builtins.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00541 |
| Opus 5 | $0.00020 | $0.00270 |
| Sonnet 5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
dynamic-skill-insertion-before-builtins 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.
How it starts
The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Dynamic Skill Insertion Before Builtins
Domain: Command Architecture Trigger: Use when commands can be discovered at runtime and must be added to a prebuilt command list without duplicating enabled entries or scrambling the established built-in ordering. Source Pattern: Distilled from reviewed command-surface, skill-discovery, and CLI capability implementations.
Core Method
First compute the user-visible base command list, then treat that enabled surface as the dedupe authority for any newly discovered runtime commands. Filter dynamic entries by stable command name against that base set so you only add commands that are truly absent for the current session. Instead of re-sorting or rebuilding the whole registry, locate the first built-in command and splice the new dynamic entries immediately before it. This keeps plugin and external discoveries ahead of the built-in block while preserving the built-ins' internal order and keeping the command surface stable across refreshes.
Key Rules
- Deduplicate against the already filtered base surface, not against every raw registered command, so disabled or unavailable commands do not wrongly block a dynamic replacement.
- Use a stable identity key such as the command name when checking whether a dynamic entry is already present.
- Keep a fast path that returns the base list unchanged when no dynamic commands exist or when all of them collapse during dedupe.
- Derive the insertion anchor from the built-in command set, then splice once at that boundary instead of globally reordering the registry.
- If no built-in boundary exists in the current list, append the dynamic entries so discovery still succeeds without special-case failures.
Example Application
If a CLI can discover new slash commands while scanning the working tree, first build the enabled command list the user can actually run, remove any discovered commands whose names already appear there, then insert the remaining discoveries just before the first built-in help or config command. The runtime additions stay visible near other extensible commands without shuffling the built-in command block on each scan.
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 · 30 lines · 41 tokens per session scan A 3f61c2faeb27
dynamic-skill-insertion-before-builtins is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 541 once invoked, about $0.0002 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 2026-08-30.
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.
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
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.
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.