sf-retune

sf-retune is a skill for Claude Code from divingsbysangam/salesforce-compound-engineering-plugin. It costs 96 tokens per session (896 once invoked), scanned A, original, MIT.

A measurement-led workflow for improving the instructions used by a Salesforce coding-agent plugin when switching to a new AI model. It compares current behaviour with a measured baseline before changing the instruction set.

In plain words
What is it for?
Use it to evaluate and retune a Salesforce skill collection for a new model, measure its behaviour, test changes and stop when a predefined quality target is met or unsupported.
Why use it?
It prevents instruction changes based only on impressions. The workflow tests whether proposed edits actually remove observed failures without introducing regressions.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Part of the sf-compound-engineering plugin — 68 skills, 1 hook, 2 MCP servers shipped together

Good fit Use it to evaluate and retune a Salesforce skill collection for a new model, measure its behaviour, test changes and stop when a predefined quality target is met or unsupported.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune
Install

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.

Any agent
npx skills add divingsbysangam/salesforce-compound-engineering-plugin --skill sf-retune
Clone the repo
git clone --depth 1 https://github.com/divingsbysangam/salesforce-compound-engineering-plugin

Made for: Claude Code.

Or install sf-compound-engineering, the plugin that ships this one along with the rest of its 68 skills, 1 hook, 2 MCP servers.

Wrote 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.

agentmods badge for sf-retune

README.md
[![agentmods](https://agentmods.dev/badge/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune/github.svg)](https://agentmods.dev/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune)
Your own site
<a href="https://agentmods.dev/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune"><img src="https://agentmods.dev/badge/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune/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.

agentmods 80×15 button for sf-retune

Your own site · 80×15
<a href="https://agentmods.dev/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune"><img src="https://agentmods.dev/badge/skills/divingsbysangam/salesforce-compound-engineering-plugin/sf-retune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.00896
Opus 5 $0.00048 $0.00448
Sonnet 5 $0.00019 $0.00179
Haiku 4.5 $0.00010 $0.00090

Measured 9d ago against content hash 937107ded342, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sf-retune 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/context.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/sf-retune/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retune a Corpus for a New Model

A corpus that degrades on a new model is a measurement problem before it is a writing problem. Reading the prose and rewriting what looks wrong produces a plausible fix list and no way to know whether any item mattered.

Outcome: a corpus whose measured behavior on the target model clears a bar registered before any change, with the regression classes removed and each removal attributable.

Done: the bar is cleared, or the run reports the specific claim it could not support. A green test suite is not done: it proves nothing broke, not that behavior improved.

Non-goal: word reduction. Leanness and performance are separate programs that happen to share a corpus, and only one of them is the result. Report completion, not word count.

Boundary: this is not sf-update, which updates the installed plugin, or sf-compound-refresh, which reconciles stale repository knowledge. sf-retune measures behavior on a target model and changes the skill corpus only when the measurements support it.

Required reads

Procedure lives in sibling files, not only in this orchestrator:

  • Phase 0: the measurement gate — check this first — read references/phase-0-the-measurement-gate-check-this-first.md before acting on this section.
  • Phase 1: mine the archive before spending a run — read references/phase-1-mine-the-archive-before-spending-a-run.md before acting on this section.
  • Phase 2: establish the noise floor before any claim — read references/phase-2-establish-the-noise-floor-before-any-claim.md before acting on this section.
  • Phase 3: audit the corpus, adversarially — read references/phase-3-audit-the-corpus-adversarially.md before acting on this section.
  • Phase 4: cut in surgical passes — read references/phase-4-cut-in-surgical-passes.md before acting on this section.
  • Phase 5: measure, then let the failure choose the next fix — read references/phase-5-measure-then-let-the-failure-choose-the-next-fix.md before acting on this section.
  • Phase 6: ship — read references/phase-6-ship.md before acting on this section.
  • Workflow shapes — read references/workflow-shapes-2.md before acting on this section.

Read the full file on GitHub · 47 lines

Changes

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.

  1. 9d ago First seen · 47 lines · 96 tokens per session scan A 937107ded342

Subscribe to this mod's changes

sf-retune is a skill published in the GitHub repository divingsbysangam/salesforce-compound-engineering-plugin (10 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 896 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens