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 headless-interactive-reconcile-paritygit 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/headless-interactive-reconcile-parity)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/headless-interactive-reconcile-parity"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/headless-interactive-reconcile-parity/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/headless-interactive-reconcile-parity"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/headless-interactive-reconcile-parity.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 | $0.00031 | $0.00450 |
| Opus 5 | $0.00015 | $0.00225 |
| Sonnet 5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
headless-interactive-reconcile-parity 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 6d 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: Headless Interactive Reconcile Parity
Domain: plugin-installation Trigger: Apply when the same extension installation lifecycle must work in both an interactive UI and a headless or automation mode. Source Pattern: Distilled from reviewed plugin, extension, and MCP synchronization implementations.
Core Method
Centralize the real install/reconcile behavior in shared lower-level helpers, then wrap it with thin mode-specific adapters. The interactive wrapper projects pending and progress state into AppState and may trigger user-facing refresh cues; the headless wrapper returns a simple changed/not-changed signal plus metrics. This preserves one source of truth for installation semantics while letting each mode expose the minimal contract its caller needs.
Key Rules
- Share the diff, reconcile, and cache-invalidation primitives between modes; only the presentation and return type should differ.
- Let interactive mode add status mapping and manual-refresh prompts, but keep those concerns out of the headless path.
- Let headless mode return a boolean or compact metric set so its caller can decide whether to refresh downstream registries.
- Preserve environment-specific options, such as seed registration or zip-cache skips, as wrapper configuration instead of forking the core reconcile algorithm.
- Whenever marketplaces change, both modes must invalidate the caches that downstream loaders depend on.
Example Application
If a coding agent can boot with a TUI or inside CI, route both startup paths through the same extension reconciler. The TUI path can paint per-source spinners, while the CI path just reports whether extensions changed and whether the caller should rebuild its command registry.
Anti-Patterns (What NOT to do)
- Do not duplicate the install algorithm in two codepaths; they will drift on skip rules, cache behavior, and error handling.
- Do not leak interactive AppState updates into headless mode or force headless callers to emulate UI state they do not have.
- Do not let headless mode skip cache invalidation just because it lacks a visual progress surface.
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.
- 6d ago First seen · 30 lines · 31 tokens per session scan A c4a36dd8a63a
headless-interactive-reconcile-parity is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 450 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.
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.
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.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.