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 reinjected-attachment-pruning-before-summarygit 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/reinjected-attachment-pruning-before-summary)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/reinjected-attachment-pruning-before-summary"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/reinjected-attachment-pruning-before-summary/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/reinjected-attachment-pruning-before-summary"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/reinjected-attachment-pruning-before-summary.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 | $0.00034 | $0.00294 |
| Opus 5 | $0.00017 | $0.00147 |
| Sonnet 5 | $0.00007 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
reinjected-attachment-pruning-before-summary 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.
What it actually says
SKILL: Reinjected Attachment Pruning Before Summary
Domain: context-management Trigger: Use when some attachment types are guaranteed to be regenerated after compaction and should not consume summary budget. Source Pattern: Distilled from reviewed reinjected-attachment pruning strategies.
Core Method
Remove only the attachment classes that the system already knows it will regenerate after compaction. This keeps the summary focused on durable conversational state and avoids paying twice for transient discovery or guidance payloads. Prune before normalization and summary generation so the saved budget reduces the compaction request itself.
Key Rules
- Prune only attachment classes with a known reinjection path.
- Apply pruning before summary generation, not after.
- Keep the pruning contract explicit so future attachment types are not stripped accidentally.
Example Application
If skill discovery attachments are recreated on the next turn after compaction, strip them before summary generation so the compactor focuses on the real debugging conversation.
Anti-Patterns (What NOT to do)
- Do not strip attachments that lack a reinjection path.
- Do not summarize large disposable attachments that will be reattached immediately afterward.
- Do not use pruning as a blanket excuse to hide important durable state.
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.
- 7d ago First seen · 28 lines · 34 tokens per session scan A fc0b395f5f29
reinjected-attachment-pruning-before-summary is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 294 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.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
ackit-context-optimization
Build budgeted context packs and trim instruction bloat for coding agents.
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
k-knowledge
Instructions for recording stable project facts in AGENTS.md or a project map. AGENTS.md is a file that stores guidance for coding agents.