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 hook-context-attachment-injectiongit 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/hook-context-attachment-injection)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/hook-context-attachment-injection"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/hook-context-attachment-injection/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/hook-context-attachment-injection"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/hook-context-attachment-injection.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 | $0.00026 | $0.00319 |
| Opus 5 | $0.00013 | $0.00160 |
| Sonnet 5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
hook-context-attachment-injection 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.
What it actually says
SKILL: Hook Context Attachment Injection
Domain: multi-agent Trigger: Use when startup hooks generate extra context that a child agent should see before it makes its first model request. Source Pattern: Distilled from reviewed startup-hook context seeding flows.
Core Method
Collect any hook-provided context while the child agent is starting, combine it into a structured metadata attachment, and inject that attachment into the initial conversation state before the query loop begins. This lets startup hooks enrich the child agent without mutating shared parent state or pretending the hook output came from the user. Keeping the payload as metadata preserves provenance and keeps the startup context easy to reason about.
Key Rules
- Gather hook output before the first request so the initial reasoning step sees the same context as later logging and transcript paths.
- Package hook output as metadata attachments, not as synthetic user or assistant text.
- Keep attachment construction deterministic so retries and resumes produce the same startup context.
Example Application
If a startup hook gathers repository hints and policy notes for a spawned coding agent, inject them as one metadata attachment before the child begins planning.
Anti-Patterns (What NOT to do)
- Do not append startup hook context after the first model turn.
- Do not mix hook metadata into user-authored content.
- Do not mutate shared parent conversation state just to deliver child-specific startup hints.
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 · 28 lines · 26 tokens per session scan A 917ad6ca3ef9
hook-context-attachment-injection is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 319 once invoked, about $0.0001 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.