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 AyushParkara/syntra --skill dispatch-agentsgit clone --depth 1 https://github.com/AyushParkara/syntraWrote 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/ayushparkara/syntra/dispatch-agents)<a href="https://agentmods.dev/skills/ayushparkara/syntra/dispatch-agents"><img src="https://agentmods.dev/badge/skills/ayushparkara/syntra/dispatch-agents/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/ayushparkara/syntra/dispatch-agents"><img src="https://agentmods.dev/badge/skills/ayushparkara/syntra/dispatch-agents.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 | $0.00039 | $0.00406 |
| Opus 5.5 | $0.00016 | $0.00162 |
| Sonnet 5.5 | $0.00008 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
dispatch-agents 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.
What it actually says
You are coordinating parallel sub-agents (via the task tool / orchestrator). Use
this only when the work genuinely splits into INDEPENDENT pieces — parallelism on
dependent work just creates conflicts.
Method:
- Decompose the goal into pieces that don't depend on each other's output. If piece B needs piece A's result, they are sequential — do NOT parallelize them.
- Scope each agent tightly: give it only the context it needs for its piece (a crisp brief), an explicit deliverable, and a done-criterion. Not the whole goal.
- Isolate writers: if two agents write files, give them separate areas (or a worktree) so they can't clobber each other.
- Bound each agent: a per-agent budget so one runaway agent can't burn the whole run (the loopguard enforces this).
- Merge: collect results, dedup, resolve any conflicts, and synthesize ONE coherent output. Note which agent produced what.
Rules:
- Parallelize for INDEPENDENT breadth (explore 3 areas, review N files), not for a single dependent chain.
- Cap the fan-out — more agents ≠ better; each costs tokens and adds merge work.
- A failed agent must not sink the batch; collect the survivors and report the gap.
- The lead (you) owns the final synthesis — agents return raw pieces, you assemble.
Good fits: explore several subsystems at once, review many files by dimension, generate N candidate approaches to compare. Bad fits: "write the parser then wire it in" (sequential), anything where order matters.
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 · 33 lines · 39 tokens per session scan A 7440cc480693
dispatch-agents is a skill published in the GitHub repository AyushParkara/syntra (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 406 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
optimization
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
gpt-image-gen
MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
coding-agent-extension-worker
Implements a single feature in the pi-mono todotools builtin extension work. Use for refactoring, continuation runtime, config resolver, prompt builder, test authoring, golden snapshots, CHANGELOG entries, and harness helpers. Does NOT do manual tmux QA.
bun-1-4
Read before a js eval cell that installs a package, spawns a server or PTY, or starts a long run, and before any bun -e, script, server, CLI, test, bundle, or package-management work: this session's eval js kernel runs Bun 1.4+ (this skill is present only when it does). Bun 1.4 ships builtins that replace 15+ npm deps…
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.