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 timjensgrossinger/threnody --skill threnody-routinggit clone --depth 1 https://github.com/timjensgrossinger/threnodyWrote 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/timjensgrossinger/threnody/threnody-routing)<a href="https://agentmods.dev/skills/timjensgrossinger/threnody/threnody-routing"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-routing/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/timjensgrossinger/threnody/threnody-routing"><img src="https://agentmods.dev/badge/skills/timjensgrossinger/threnody/threnody-routing.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 | $0.00046 | $0.00658 |
| Opus 5 | $0.00023 | $0.00329 |
| Sonnet 5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
threnody-routing 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threnody routing
Threnody is a meta-harness: the MCP host shell executes work; Threnody coordinates routing, planning, and optional utility delegation.
The portable contract is host_spawn / host_spawn_waves. Claude Code Dynamic
Workflow emission is an optional Claude-only optimization; do not depend on it
for behavior that must work across Codex, Cursor, Copilot, Junie, or OpenCode.
Default path (always try first)
- Call
route_task(task=...)(MCP: Threnody). - Read
execution_hint.mode:host_native— use hostTask/Agent(host_spawnin response).delegate— only whendelegation_utilities_enabledis true and targets are utilities.
- Follow
recommended_actionandhost_native_model/host_native_method.
Handoff precedence
When a prior plan_task, fleet_plan, or execute_swarm response includes host_spawn_waves or host_execution_contract: spawn_subagents, always spawn per agent — host_native_method: direct_edit does not apply.
direct_edit is only for lone route_task results with no pending handoff (execution_hint.active_handoff is not set).
Utility-only delegation
execute_subtask is not general cross-CLI orchestration.
| Condition | Result |
|---|---|
delegation_utilities_enabled: false |
No utility delegation; host-native only |
Enabled + provider_id in allowlist |
OpenCode, Aider, local loopback endpoints |
| Host CLI as target (Copilot, Codex, Cursor, Junie, Claude) | Hard blocked — use host_spawn |
| Same-host caller + same provider | HostNativeRequired + host_spawn payload |
Config (installed ~/.local/lib/threnody/config.yaml):
providers:
delegation_utilities_enabled: false
delegation_utilities:
- opencode
- aider
Routing guard (guarded mode)
When routing_policy is guarded (opt-in via mode: guarded or per-shell override):
- Call
route_taskbefore non-exempt code edits. - Markdown and instruction files are exempt by default.
- After routing, host-native execution first — the guard is coordination, not a delegation mandate.
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 · 68 lines · 46 tokens per session scan A 0e5448f297a2
threnody-routing is a skill published in the GitHub repository timjensgrossinger/threnody (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 46 tokens to every session and 658 once invoked, about $0.0002 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
personetta-set-active
Switches the active Personetta persona via set-active. The target tool is auto-detected from the host agent (Claude Code here), so no --format is needed. Use when the user asks to change recipe, switch persona, or set active role.
personetta-current
Reports the active Personetta recipe id using the installed CLI. The host agent (Claude Code here) is auto-detected. Use when the user asks for their current persona, active recipe, or which Personetta role is on.
personetta-list
Lists Personetta recipes (and optionally roles) using the installed Personetta CLI. Use when the user asks what recipes or personas exist before switching.
curate-a-team-library
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful whyHere notes, and create a starter pack once the first pass is solid.
migrate-skills-between-libraries
Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.
review-a-skill
Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.