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 ChrisLamDev/hermes-core-skills --skill autonomous-work-signalinggit clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skillsWrote 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/chrislamdev/hermes-core-skills/autonomous-work-signaling)<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/autonomous-work-signaling"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/autonomous-work-signaling/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/chrislamdev/hermes-core-skills/autonomous-work-signaling"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/autonomous-work-signaling.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 | $0.00015 | $0.01600 |
| Opus 5 | $0.00008 | $0.00800 |
| Sonnet 5 | $0.00003 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
autonomous-work-signaling 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 10d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Work Signaling Protocol
The Problem: "Empty Rocket" 🚀
When a user authorizes the agent to work autonomously across sessions (e.g., "執行完所有 REVIEW 指引先通知我"), multiple coordination failures can occur:
Failure #1: The "Empty 🚀"
- Agent sends 🚀 (rocket) signaling "working"
- But agent is actually waiting for a "continue" trigger from the user
- No tool calls fire → zero token consumption
- User thinks work is happening; nothing is
Failure #2: Silent Tool Exhaustion
- Agent works hard, uses all tool calls, outputs final response
- Final response doesn't clearly say "I'm out of energy, please say continue"
- User waits indefinitely, not knowing the agent needs another trigger
Failure #3: User-As-Battery
- User has to say "繼續" after every tool-call-limit exhaustion
- This was the original fix attempt, but it defeated the purpose of autonomy
- User felt like a "battery recharger"
Root Cause
Hermes Agent is a conversational AI, not a background daemon. It:
- Only fires tool calls when it receives a user message (trigger)
- Has a tool-call limit per turn (typically 50-80 calls)
- Cannot "keep running" between messages
- An emoji response is just a message — it does not consume tokens unless followed by tool calls
The Fix: Clear Work-State Signaling
State Machine
IDLE → [user says "继续" / "start"] → 🚀 LAUNCHING (acknowledgment + first action)
→ 🔄 WORKING (tool calls firing, token consuming)
→ (tool limit reached, one more result to process)
→ ⚡ EXHAUSTED (final response: state + "% complete" + "continue?" prompt)
→ waiting for user → 🚀 LAUNCHING → ...
→ ✅ COMPLETE (all tasks done, detailed report)
Signal Definitions
| Signal | Meaning | User Action |
|---|---|---|
| 🚀 | Received your trigger. Starting the next batch of work. First tool call just fired or is about to. | None — let agent work. Do NOT send another message. |
| 🔄 | Mid-work status update (optional, only if needed). Agent is still within its tool call budget. | None. |
| ⚡ | Out of energy. Hit tool call limit. Work saved. Ready for next trigger. Has done X% of the remaining task. | Send "繼續" or "continue" to re-trigger. |
| ✅ | All tasks complete. Detailed report follows. | Read report. Give further instructions. |
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.
- 10d ago First seen · 142 lines · 15 tokens per session scan A 84c0a2f519db
autonomous-work-signaling is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,600 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 2026-08-31.
Other skills, from other repositories
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
autonomous-run
Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
research-archival
Scrape AI research URLs, archive with frontmatter, create GitHub Issues with identity verification.