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 vitaliikapliuk/modelharness --skill delegation-triggersgit clone --depth 1 https://github.com/vitaliikapliuk/modelharnessWrote 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/vitaliikapliuk/modelharness/delegation-triggers)<a href="https://agentmods.dev/skills/vitaliikapliuk/modelharness/delegation-triggers"><img src="https://agentmods.dev/badge/skills/vitaliikapliuk/modelharness/delegation-triggers/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/vitaliikapliuk/modelharness/delegation-triggers"><img src="https://agentmods.dev/badge/skills/vitaliikapliuk/modelharness/delegation-triggers.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 | $0.00314 |
| Opus 5 | $0.00023 | $0.00157 |
| Sonnet 5 | $0.00009 | $0.00063 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
delegation-triggers 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 12d 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
Delegation Triggers
Opus 4.8 is documented to under-reach for subagents. Apply these rules instead of intuition.
Delegate (spawn subagents, in parallel where independent) when:
- Work fans out across independent items: reading/searching many files, auditing several modules, running several independent investigations.
- You need a broad search where only the conclusion matters (use a read-only explore subagent; you keep the answer, not the file dumps).
- You need fresh-context verification of your own work (see verification-loop).
- Two or more workstreams have no shared state and no ordering dependency — launch them in one message so they run concurrently.
Work directly when:
- A single file read or a known-location lookup would answer the question.
- Edits are sequential and each depends on the previous result.
- The task is small enough that subagent setup costs more than it saves.
How
- Give each subagent a self-contained brief: goal, exact scope, what to return.
- Don't duplicate a delegated search yourself — wait for the result.
- Prefer asynchronous delegation: keep working on the main thread while subagents run; intervene only if one goes off track.
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.
- 12d ago First seen · 30 lines · 46 tokens per session scan A 2fd22e4fff34
delegation-triggers is a skill published in the GitHub repository vitaliikapliuk/modelharness (38 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 314 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 2026-08-30.
Other skills, from other repositories
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
remind
A correction helper that checks which project rules or required steps were missed and loads the relevant guidance.
adr
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/ /adr- - .md with a 3-digit zero-padded number. Handles the Superseded case: bidirectional linking when a new ADR replaces an old one. Use when: recording why an architectural…