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 agentmods add skills/heretyc/subagent-mcp/model-profilernpx skills add Heretyc/subagent-mcp --skill model-profilergit clone --depth 1 https://github.com/Heretyc/subagent-mcpWrote 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/heretyc/subagent-mcp/model-profiler)<a href="https://agentmods.dev/skills/heretyc/subagent-mcp/model-profiler"><img src="https://agentmods.dev/badge/skills/heretyc/subagent-mcp/model-profiler.svg" alt="Measured on agentmods" 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 | $0.00347 | $0.03866 |
| Opus 5 | $0.00173 | $0.01933 |
| Sonnet 5 | $0.00069 | $0.00773 |
| Haiku 4.5 | $0.00035 | $0.00387 |
Grade A, and why
model-profiler 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 3d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Profiler
Impartially profile the sub-agent fleet against the FIXED 14 work-categories (directly benchmarked parents + 4 composite-inferred) when a new model ships (or on demand). The skill is the impartial judge of all models: it discovers the models, gathers their public benchmarks, and ranks each model+effort pairing per category : it does not decide what the categories are.
Input = the profiling scope (in-scope provider families + recent window) confirmed in Phase 0
or supplied by the standing repository profile when its exact trigger matches.
Output = EXACTLY 3 persisted artifacts (src/routing-table.json, src/routing-table-audit.json,
research-seed-sites.json); nothing else persists. See the Output Contract below.
This SKILL.md is the index : load only the current phase's detail leaf, never all of them. Each md file stays <=200 lines (AGENTS.md cap).
Required Runner (read first)
Run ONLY on the highest available flagship model the operating provider offers (whatever
that currently is), at its highest OR second-highest effort setting (i.e. a top-tier
reasoning model at high effort; the provider-equivalent top model+effort otherwise). Note:
binding an explicit runner model/effort for sub-agents is itself gated : see the gating
preamble in references/dispatch-mechanics.md (smart mode rejects selector-bearing launches
unless the user-approved-overrides window is open). It is
orchestrator-only: the runner dispatches every research/judging/validation step via
mcp__subagent-mcp__launch_agent and must sustain multi-phase reasoning across the whole
run. Never run on Haiku, a non-flagship tier, an effort below second-highest, or any
model lacking sub-agent-launch support or long-horizon reasoning : these silently
degrade the pipeline. If the runner does not meet this bar, halt and escalate to the
owner; do not run it. (Runner requirement only : distinct from invariant #2's ban on the
skill naming a preferred model for the JUDGED routing output.)
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/adversarial-loop.md 7.3 KB
- references/artifact-map.md 4.2 KB
- references/benchmark-sources.md 12 KB
- references/category-derivation.md 3.0 KB
- references/citations-labels.md 3.0 KB
- references/decompose-update.md 5.7 KB
- references/dispatch-mechanics.md 8.9 KB
- references/execution-lifecycle.md 4.9 KB
- references/overview.md 10 KB
- references/phase-0-consent.md 13 KB
- references/phase-1-research.md 14 KB
- references/phase-2-synthesis.md 7.8 KB
- references/pipeline-and-output.md 1.8 KB
- references/provider-json-emission.md 6.7 KB
- references/tier-ranking-and-scoring.md 12 KB
- references/tier-ranking-and-scoring/01-sops.md 6.1 KB
- references/validation.md 9.1 KB
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.
- 3d ago First seen · 178 lines · 0 tokens per session scan A b3f57c269821
model-profiler is a skill published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 347 tokens to every session and 3,866 once invoked, about $0.0017 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
planflow
Draft a plan and get it approved as an editable flowchart in the user's browser before executing. Use when the user asks to plan a task with PlanFlow, or wants to review, edit, or approve a plan before any code changes are made.
seo-strategy
Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…
implement-factory
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…