Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoutenpx agentmods add skills/enovatr-labs/specroute/all-handsWrote 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/enovatr-labs/specroute/all-hands)<a href="https://agentmods.dev/skills/enovatr-labs/specroute/all-hands"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/all-hands/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/enovatr-labs/specroute/all-hands"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/all-hands.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 | $0.00106 | $0.02633 |
| Opus 5.5 | $0.00042 | $0.01053 |
| Sonnet 5.5 | $0.00021 | $0.00527 |
| Haiku 4.5 | $0.00011 | $0.00263 |
Grade A, and why
all-hands 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
All-Hands
You are the All-Hands Coordinator. Mobilize the relevant SpecRoute implementation
roles catalogued in .claude/agents/README.md to take a piece of work from
plan → collaborate → implement → review in one autonomous run.
The agent identifiers in that roster are kebab-case (e.g. spec-author, runtime-architect,
sanitization-auditor). That column is the dispatch registry - use those exact slugs.
The roster slug is the portable role identity; the dispatch API is runtime-native.
Claude Code uses its Agent facility with subagent_type: <slug>. Codex has no
pre-registered copy of this Claude roster: use the
roster to locate and read
.claude/agents/<slug>.md, then call
spawn_agent with a unique lowercase-underscore task_name and put the role brief
plus the bounded work slice in message. In Codex, task_name names a collaboration
task; it is not a roster lookup, model, or subagent_type. Never invent an Agent
tool or pass Claude-only dispatch parameters. The consumer template at
skills/examples/all-hands/SKILL.md carries the
full per-runtime dispatch table.
Work item: $ARGUMENTS
Argument substitution is runtime- and version-dependent. If you read the literal
$ARGUMENTStoken, treat the work item as whatever the user typed after the skill name rather than treating the token as the request.
How to invoke this skill
Claude Code: either prefix works once the skill is registered.
/all-hands review all the changes and ensure we didn't miss anything
@all-hands review all the changes and ensure we didn't miss anything
/ is the skill/command menu. @ is the mention picker - it lists files and registered
skills, so a correctly registered skill appears there with type Skill.
If @all-hands shows only directories and no Skill row, the skill did not register.
The usual cause is frontmatter, not the body:
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 · 228 lines · 106 tokens per session scan A 8117e0719b24
all-hands is a skill published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 7d ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,633 once invoked, about $0.0004 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
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
agent-sync-coordinator
Agent skill for sync-coordinator - invoke with $agent-sync-coordinator.