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 progress-first-tool-emissiongit 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/progress-first-tool-emission)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/progress-first-tool-emission"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/progress-first-tool-emission/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/progress-first-tool-emission"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/progress-first-tool-emission.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 | $0.00027 | $0.00439 |
| Opus 5 | $0.00014 | $0.00219 |
| Sonnet 5 | $0.00005 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
progress-first-tool-emission 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.
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: Progress-First Tool Emission
Domain: tool-orchestration
Trigger: Streaming tool runners that produce progress messages or status updates alongside final tool results.
Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Track progress messages separately from final results by adding them to a dedicated buffer as soon as they arrive, and yield those messages to the user immediately, even while the tool is still running. Keep the final tool result buffered until the tool completes, and only then release it respecting the queue order. Handle cancellations, sibling errors, or streaming fallbacks by emitting synthetic tool error messages that describe the reason before closing the tool's slot, so the user sees a consistent progression of updates.
Key Rules
- Emit progress lines instantly from their pendingProgress buffer while the tool is active; do not wait for full completion for updates that clarify status.
- When errors occur (user interrupt, streaming fallback, sibling error), craft a synthetic tool_result message explaining the cause and flush it before marking the tool completed.
- Keep context modifiers and results separated so progress does not mutate the shared context until the tool has fully finished and the ordered slot is ready to release new state.
Example Application
For a CLI agent running shell commands that stream stdout/stderr, use this pattern so the UI gets progress-level updates (stream lines, spinner ticks) immediately, yet the final success/failure summary appears once the command finishes and in the correct sequential order relative to other tools.
Anti-Patterns (What NOT to do)
- Treat progress output as part of the final result and hold it until the tool completes, which prevents the user from seeing real-time feedback.
- Drop synthetic error messages when canceling sibling tools, leaving the UI without an explanation for the aborted run.
- Let progress emissions mutate context or completion state before the tool is fully done, which can leave the shared context inconsistent.
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 · 27 tokens per session scan A 836c5987b058
progress-first-tool-emission is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 439 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.