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 ordered-streaming-tool-executiongit 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/ordered-streaming-tool-execution)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/ordered-streaming-tool-execution"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/ordered-streaming-tool-execution/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/ordered-streaming-tool-execution"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/ordered-streaming-tool-execution.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 | $0.00028 | $0.00425 |
| Opus 5 | $0.00014 | $0.00212 |
| Sonnet 5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
ordered-streaming-tool-execution 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: Ordered Streaming Tool Execution
Domain: tool-orchestration
Trigger: Streaming toolUse input where progress must be shown in the original queue order, even if some tools run concurrently.
Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Maintain an ordered queue of tracked tools whose statuses include queued, executing, and completed. When a tool becomes eligible, start it only if no incompatible executor is running (non-concurrency-safe tools block the queue) and mark it executing. Buffer results and progress messages per tool and never yield them until all previous tools have finished; only then append their buffered messages to the output stream in the original order. This preserves a deterministic user view while still allowing safe tools to run in parallel.
Key Rules
- Represent each tool use with a tracked descriptor holding queue position, assistant metadata, context modifiers, pending progress, and results.
- Only start tools when can execute tool permits; concurrent-safe ones may run alongside others but non-safe ones must wait for the queue drain.
- Buffer output (results/progress/heuristics) and flush it only after every earlier tool has resolved, so ordering cannot be disrupted by race conditions.
Example Application
Implement a streaming tool runner for a conversational agent by streaming helper tasks into the executor, letting concurrency-safe tools run in parallel, and deferring emission until all prior toolUse entries have completed so the transcript matches the request order.
Anti-Patterns (What NOT to do)
- Emit tool results as soon as they arrive in the background, which scrambles the perceived order and confuses the user.
- Ignore is concurrency safe and start mutually exclusive tools simultaneously, risking inconsistent shared resources.
- Fail to keep pending progress separate and merge them out of order, which causes partial updates to interleave incorrectly.
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 · 28 tokens per session scan A 6b5bfb378376
ordered-streaming-tool-execution is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 425 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.