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 dead-path-update-skippinggit 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/dead-path-update-skipping)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/dead-path-update-skipping"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/dead-path-update-skipping.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 | $0.00037 | $0.00406 |
| Opus 5 | $0.00018 | $0.00203 |
| Sonnet 5 | $0.00007 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
dead-path-update-skipping 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: Dead Path Update Skipping
Domain: extensions-mcp
Trigger: Use when update candidates come from local paths that may disappear across checkouts, but existing materialized state should remain usable until a valid replacement exists.
Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.
Core Method
Before running an update from a local path, verify that the declared path still exists. If the action is an update and the current materialized entry is still valid, skip the update rather than turning a transient path mismatch into a failed reinstall. This preserves the working materialized state in multi-checkout or ephemeral-path scenarios while still surfacing missing paths for truly absent entries.
Key Rules
- Only apply this skip to updates where a materialized entry already exists; missing entries should still surface real errors.
- Check path existence after normalization so you validate the exact path the reconciler would use.
- Record skipped updates distinctly from failures so operators know the existing entry was intentionally preserved.
- Limit the exception to local-path sources; remote sources need normal failure handling.
- Log the reason for the skip so future debugging can tell path drift from install breakage.
Example Application
If a developer switches away from a temporary worktree that contained a local marketplace path, keep the previously materialized marketplace entry instead of failing an update against the now-missing worktree path. The next valid local path or explicit reinstall can replace it later.
Anti-Patterns (What NOT to do)
- Do not attempt updates from dead local paths just to fail loudly; you destroy signal-to-noise while preserving nothing.
- Do not apply this rule to brand-new missing entries; if nothing working exists yet, the user needs the error.
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 · 29 lines · 37 tokens per session scan A 788ef316099f
dead-path-update-skipping is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 406 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.