mode-gated-reconcile-skip-filter

mode-gated-reconcile-skip-filter is a skill for Claude Code, Codex from ychampion/cskill-agents. It costs 35 tokens per session (401 once invoked), scanned A, original, MIT.

A reconciliation filter that lets each runtime mode skip unsupported sources and record them separately from failures.

In plain words
What is it for?
It helps extension managers handle installations and updates across runtimes with different capabilities.
Why use it?
It prevents unsupported items from being reported as installation errors while preserving one shared reconciliation process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps extension managers handle installations and updates across runtimes with different capabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter
Install

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.

Any agent
npx skills add ychampion/cskill-agents --skill mode-gated-reconcile-skip-filter
Clone the repo
git clone --depth 1 https://github.com/ychampion/cskill-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mode-gated-reconcile-skip-filter

README.md
[![agentmods](https://agentmods.dev/badge/skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter/github.svg)](https://agentmods.dev/skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter)
Your own site
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter/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.

agentmods 80×15 button for mode-gated-reconcile-skip-filter

Your own site · 80×15
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/mode-gated-reconcile-skip-filter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00401
Opus 5 $0.00017 $0.00200
Sonnet 5 $0.00007 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 7d ago against content hash 0755395e64e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mode-gated-reconcile-skip-filter 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 7d 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.

agents/claude-code/skills/mode-gated-reconcile-skip-filter/SKILL.md · 29 lines

What it actually says

SKILL: Mode-Gated Reconcile Skip Filter

Domain: extensions-mcp
Trigger: Apply when a shared reconcile engine runs in multiple runtime modes, but some modes cannot support every source type or transport. Source Pattern: Distilled from reviewed extension lifecycle and source-reconciliation patterns.

Core Method

Keep one shared reconcile pipeline, but let callers inject an optional skip predicate that reflects mode-specific capabilities. The reconciler still computes the full worklist, then filters unsupported items into a skipped result instead of misreporting them as failures or forcing wrappers to fork the install algorithm. That preserves a single source of truth for install/update behavior while allowing constrained runtimes to stay honest about what they cannot process.

Key Rules

  • Put capability checks behind an injected skip predicate rather than branching the whole reconcile implementation.
  • Record skipped items explicitly so operators can distinguish "unsupported here" from true install failures.
  • Apply the skip filter after the worklist is built so visibility into intended changes remains intact.
  • Keep logging around skipped items; silent skipping hides portability gaps between modes.
  • Preserve identical install/update semantics for supported items across all modes.

Example Application

If a desktop agent can install extensions from local folders and remote archives but a serverless worker only supports archives, let the worker pass a skip predicate for local-folder sources. The shared reconciler still handles archives the same way, while skipped folder sources are reported cleanly instead of failing the whole run.

Anti-Patterns (What NOT to do)

  • Do not duplicate the entire reconciler per mode just to exclude a few unsupported source types.
  • Do not treat unsupported sources as generic failures; that obscures whether the issue is capability mismatch or broken input.
Changes

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.

  1. 7d ago First seen · 29 lines · 35 tokens per session scan A 0755395e64e2

Subscribe to this mod's changes

mode-gated-reconcile-skip-filter is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 401 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 2026-09-03.