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 user-input-before-thread-attachmentsgit 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/user-input-before-thread-attachments)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/user-input-before-thread-attachments"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/user-input-before-thread-attachments/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/user-input-before-thread-attachments"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/user-input-before-thread-attachments.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 | $0.00412 |
| Opus 5.5 | $0.00010 | $0.00165 |
| Sonnet 5.5 | $0.00005 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
user-input-before-thread-attachments 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: User Input Before Thread Attachments
Domain: attachment-pipeline Trigger: When attaching contextual artifacts in response to user input, run that work first so any derived triggers exist before later attachment builders execute. Source Pattern: Distilled from reviewed attachment-pipeline ordering and derived-trigger dependency implementations.
Core Method
Treat user-input-driven attachment producers as dependencies for the broader attachment phase. Start by collecting the attachments that inspect user text directly, such as file mentions, MCP references, or other explicit user-specified artifacts, and wait for that set to finish. Only then should the second-stage thread-safe attachment builders run, because they may depend on triggers or metadata harvested from the first phase. This ordering prevents downstream attachment builders from running too early against incomplete state.
Key Rules
- Build the user-input attachment group first, including everything that inspects raw user text or explicit user references.
- Wait for the entire first-phase attachment group to complete before starting second-phase attachment logic.
- Only once the user attachment future settles should you start the second-stage attachment list (queued actions, time-based context, memory lookups, and similar follow-on builders).
- Keep the dependency notes close to the ordering boundary so future maintainers do not accidentally reorder the pipeline.
Example Application
If a request mentions files and also triggers a secondary memory lookup, resolve the file mentions first and wait for that work to complete. Only then run the dependent memory attachment builder so it sees the full set of requested paths.
Anti-Patterns (What NOT to do)
- Do not launch the second-phase attachment builders before the user-input phase finishes; doing so lets dependent builders execute with empty or partial triggers.
- Do not assume derived trigger state will “fill in later”; the pipeline must wait on the user-input phase to preserve the dependency ordering.
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 · 28 lines · 26 tokens per session scan A a99ef23d0663
user-input-before-thread-attachments is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 412 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.