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 tonbistudio/hermes-multi-agent-workflow --skill triage-orchestratorgit clone --depth 1 https://github.com/tonbistudio/hermes-multi-agent-workflowWrote 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/tonbistudio/hermes-multi-agent-workflow/triage-orchestrator)<a href="https://agentmods.dev/skills/tonbistudio/hermes-multi-agent-workflow/triage-orchestrator"><img src="https://agentmods.dev/badge/skills/tonbistudio/hermes-multi-agent-workflow/triage-orchestrator/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/tonbistudio/hermes-multi-agent-workflow/triage-orchestrator"><img src="https://agentmods.dev/badge/skills/tonbistudio/hermes-multi-agent-workflow/triage-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 100 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00090 | $0.01216 |
| Opus 5 | $0.00045 | $0.00608 |
| Sonnet 5 | $0.00018 | $0.00243 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
triage-orchestrator 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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage orchestrator (thin driver)
Design contract: fat engine, thin skill. Anything deterministic — dedup lookup, applying the score threshold, route resolution, building research fan-out, building the prep/fulfillment chains, choosing workspaces — is a call into
engine/. You (the model) only do what needs judgment. Do NOT re-derive the pipeline shape in prose here; it lives intriage.yaml. Readdocs/01-architecture.mdanddocs/05-pipeline-stages.md.
All commands below run from the repo root with triage.yaml present.
TRIAGE_CONFIG, TRIAGE_VAULT_DIR, and HERMES_KANBAN_DB are honored.
Trigger
A new intake task assigned to you appears on the triage board. Its body is a
path to a scout report.
Procedure
1. Parse intake
Read the report file. Parse it into candidates (engine/intake_parser.py shape).
2. Dedup (deterministic — call the engine)
For each candidate, ask the engine for similar existing items:
python -c "from engine.config import TriageConfig; from engine.engine import TriageEngine; \
import json,sys; e=TriageEngine(TriageConfig.load()); \
print(json.dumps([m.__dict__ for m in e.dedup(sys.argv[1])]))" "<candidate title + claim>"
duplicate→ append the new source to the existing item, stop. Don't re-research.possible→ note it, continue, re-check after research.new→ create a vault item (ItemVault.create_item) withstatus: triage.
3. Score (judgment + engine validation)
This is YOUR judgment. Get the rubric prompt from the engine
(TriageEngine.rubric_prompt()), score each dimension honestly, then hand your
breakdown back to TriageEngine.score(breakdown) to apply the maxes + threshold.
Write score / score_breakdown to the item file regardless of outcome.
- Below threshold → shelve automatically. Do not bother the human.
- At/above → continue.
(For a deterministic/offline pass you may instead call
TriageEngine.score_heuristic(candidate) — see engine/scoring.py.)
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.
- 11d ago First seen · 106 lines · 90 tokens per session scan A 1f6fac86e1a0
triage-orchestrator is a skill published in the GitHub repository tonbistudio/hermes-multi-agent-workflow (461 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,216 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.