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 mode-gated-reconcile-skip-filtergit 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/mode-gated-reconcile-skip-filter)<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.
<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>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 | $0.00035 | $0.00401 |
| Opus 5.5 | $0.00014 | $0.00160 |
| Sonnet 5.5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
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 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: 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.
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 · 29 lines · 35 tokens per session scan A 0755395e64e2
mode-gated-reconcile-skip-filter is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 401 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.