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 zjunlp/Mechanist --skill steering-coefficient-tuninggit clone --depth 1 https://github.com/zjunlp/MechanistWrote 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/zjunlp/mechanist/steering-coefficient-tuning)<a href="https://agentmods.dev/skills/zjunlp/mechanist/steering-coefficient-tuning"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/steering-coefficient-tuning.svg" alt="Measured on agentmods" 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 analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00288 | $0.00825 |
| Opus 5 | $0.00144 | $0.00413 |
| Sonnet 5 | $0.00058 | $0.00165 |
| Haiku 4.5 | $0.00029 | $0.00082 |
Grade A, and why
steering-coefficient-tuning 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 8d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steering Coefficient Tuning
The point
A steering coefficient that is too small does nothing; one that is too large damages the model's general ability and breaks fluent generation. You want the moderate range in between, and you find it by sweeping.
Keep the following in mind:
-
The best coefficient depends on where you intervene — different layers (and different sites) need different coefficients. A value tuned at one layer does not transfer to another.
-
Mid layers usually work best, because "semantic maturity" varies with depth (task-dependent):
- Early layers — closer to tokens / local patterns.
- Mid layers — more often carry high-level control signals: behavior, intent, style, refusal.
- Late layers — closer to logits and surface token choice, so even a slightly large coefficient at a late layer tends to produce repeated tokens, format-symbol spam, or broken semantics.
-
Sweep coarse-to-fine.
- Start wide. Try a broad, geometrically spaced range — e.g.
[1, 2, 4, 8, 16, 32, …]. - Escalate before abandoning. At a given layer, if a small coefficient does not work, try a larger one. Only when raising the coefficient still does not work and the side effects have become severe — the generated text is entirely worthless — should you switch the feature, switch the layer, or switch to a different method.
- Then narrow. Once a promising range is located, progressively shrink it to find the optimum.
- Start wide. Try a broad, geometrically spaced range — e.g.
-
Score every sweep point on a target metric and a fluency / general-ability / specific-function metric; keep the Pareto-optimal candidates.
-
Stopping without a coefficient that meets the criteria is not allowed. If no coefficient passes and you stop anyway, the result is not a negative finding — you must record an
open_items[]warning: "no coefficient met the criteria; the coefficient range may not have been swept widely enough, and this is a likely cause of the failure — recommend manually sweeping beyond the recorded bounds<β_min>…<β_max>before treating the result as established."
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.
- 8d ago First seen · 33 lines · 288 tokens per session scan A b3dfa23c7726
steering-coefficient-tuning is a skill published in the GitHub repository zjunlp/Mechanist (72 stars, last pushed 12d ago), licensed MIT. It adds 288 tokens to every session and 825 once invoked, about $0.0014 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
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
create-atomic-context-provider
Build a BaseDynamicContextProvider that injects a named, titled block into an agent's system prompt at every run() — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent dynamic context", "wire…
synalinks
Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired) — DataModel/Field/Input, JSON operators (+ & | ^ ), synalinks.ops, LanguageModel/EmbeddingModel and provider prefixes (openai/anthropic/ollama/groq/openrouter/bedrock/...); the Program class and its four building APIs…
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint.
nanoresearch-planning
Produce an experiment blueprint from a research hypothesis.