so-what-sharpener

so-what-sharpener is a skill for Claude Code from daddia/claude-for-strategy. It costs 61 tokens per session (633 once invoked), scanned A, original, MIT.

A skill that turns observations or data points into clear insights by linking each fact to its implication and decision meaning.

In plain words
What is it for?
Use it when someone asks what the findings mean, needs an insight sharpened, or wants overlapping observations combined. It can also mark facts that do not support a useful insight.
Why use it?
It prevents reports from stopping at a list of facts or claiming conclusions that the evidence does not support.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the consulting plugin — 9 skills shipped together

Good fit Use it when someone asks what the findings mean, needs an insight sharpened, or wants overlapping observations combined. It can also mark facts that do not support a useful insight.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daddia/claude-for-strategy/so-what-sharpener
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 daddia/claude-for-strategy --skill so-what-sharpener
Clone the repo
git clone --depth 1 https://github.com/daddia/claude-for-strategy

Made for: Claude Code.

Or install consulting, the plugin that ships this one along with the rest of its 9 skills.

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 so-what-sharpener

README.md
[![agentmods](https://agentmods.dev/badge/skills/daddia/claude-for-strategy/so-what-sharpener/github.svg)](https://agentmods.dev/skills/daddia/claude-for-strategy/so-what-sharpener)
Your own site
<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/so-what-sharpener"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/so-what-sharpener/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 so-what-sharpener

Your own site · 80×15
<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/so-what-sharpener"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/so-what-sharpener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 633 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.
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 $0.00061 $0.00633
Opus 5 $0.00030 $0.00316
Sonnet 5 $0.00012 $0.00127
Haiku 4.5 $0.00006 $0.00063

Measured 10d ago against content hash 65a21ce49749, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

so-what-sharpener 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.

consulting/skills/so-what-sharpener/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

So-What Sharpener

When to use

Sharpen observations into insight via observation → implication → insight chain. Smallest Minto unit before full narrative.

What this skill does not do

  • Does not skip implication step — catches lazy insights.
  • Does not force insight on non-load-bearing facts — "No insight earned" section.
  • Does not build full pyramid — use narrative-builder for that.

Preconditions

Input If missing
Observations or data points Ask user to list
Decision context Ask what decision insights must support

Provisional mode

Missing decision context: implications literal only; insights tagged [review].

Trust spine

  • Analytical Rigor (mandatory): Explicit three-step chain per point; merge redundant insights.
  • Per trust-conventions.md on tagged figures in observations.

Workflow

For each observation:

  1. State observation unchanged.
  2. State implication (literal).
  3. State insight (so-what for decision).
  4. Flag observations with no earned insight.
  5. Group and merge overlapping insights.

Output format

Observation: [...]
  → Implication: [...]
  → Insight: [...]

No insight earned: [...]

Worked example

Input: "Mid-tier ARPU down 12% QoQ." Decision: pricing revert?

Excerpt: Implication: mid-tier spending less; Insight: increase likely priced out intended segment — reconsider pricing [review].

Quality checks before delivering

  • Three-step chain per point
  • No insight earned section when applicable
  • Overlaps merged

Propose profile update

When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/consulting/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /consulting:practice-setup auto-applies a full profile write.

Outputs

Read the full file on GitHub · 84 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. 10d ago First seen · 84 lines · 61 tokens per session scan A 65a21ce49749

Subscribe to this mod's changes

so-what-sharpener is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 633 once invoked, about $0.0003 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

swarmclaw

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

swarmclawai/swarmclaw · 67 tokens

spec-herdr-review

Run visible multi-agent spec reviews in Herdr through interactive agent CLIs such as Claude, Codex, Copilot/GLM, or Grok/Composer. Supports two modes — a spec review (the design, before implementation) and an implementation review (the implemented diff vs the spec, after the calling model has built it). Ask for…

stewartcelani/skills · 88 tokens

gpmc

Read-only Active Directory Group Policy inventory via LDAP — list GPOs, show OU/site links (enabled/disabled/enforced), find unlinked GPOs, search by name, and gpresult for the current user. Use when the user asks about GPOs, Group Policy, GPMC, linked vs unlinked policies, RSoP, what applies to this user, or runs…

stewartcelani/skills · 115 tokens

claude-session

Find and inspect local Claude Code conversations by session GUID, title, phrase, or recent activity. Use when the user runs /claude-session, asks what Claude Code work they have been doing lately, says a Claude Code conversation died, ran out of context, crashed, or exhausted usage, wants to resume a named…

stewartcelani/skills · 80 tokens

grok-session

Find and inspect local Grok CLI conversations by session GUID, title, phrase, or recent activity. Use when the user runs /grok-session, asks what Grok work they have been doing lately, says a Grok conversation died, ran out of context, crashed, or exhausted usage, wants to resume a named session, or wants to continue…

stewartcelani/skills · 85 tokens

codex-session

Find and inspect local Codex task conversations, including by session GUID, title, recent activity, or a phrase from the conversation. Use when the user runs /codex-session, says a prior Codex conversation died or ran out of context, wants to resume a named task, asks what a local Codex task did, or wants to continue…

stewartcelani/skills · 81 tokens