define-perspectives

define-perspectives is a skill for Claude Code from daddia/claude-for-strategy. It costs 53 tokens per session (2,049 once invoked), scanned A, original, MIT.

A guide for choosing the perspectives and causal-chain order in a balanced scorecard, a framework for organizing an organization's strategy and measures. It considers the organization's mission, sector, and operating context.

In plain words
What is it for?
Use it before drafting strategy-map objectives when the scorecard structure or top perspective is unclear. It helps compare standard and custom perspective sets.
Why use it?
It prevents teams from choosing standard categories without deciding which results matter most and how the other perspectives support them.

Skill for Claude Code

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

Part of the balanced-scorecard plugin — 7 skills, 1 agent, 13 MCP servers shipped together

Good fit Use it before drafting strategy-map objectives when the scorecard structure or top perspective is unclear. It helps compare standard and custom perspective sets.

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

Made for: Claude Code.

Or install balanced-scorecard, the plugin that ships this one along with the rest of its 7 skills, 1 agent, 13 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 define-perspectives

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/define-perspectives"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/define-perspectives.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,049 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 $0.00053 $0.02049
Opus 5 $0.00026 $0.01025
Sonnet 5 $0.00011 $0.00410
Haiku 4.5 $0.00005 $0.00205

Measured 8d ago against content hash a1ec62a6a1dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

define-perspectives 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.

balanced-scorecard/skills/define-perspectives/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Define Perspectives

When to use

For strategy office or FP&A practitioners deciding the perspective set and causal-chain order before drafting objectives. The real decision isn't naming four boxes — it's which perspective sits at the top of the causal chain, because every other objective ultimately has to serve that end.

What this skill does not do

  • Does not draft objectives — output feeds /balanced-scorecard:build-strategy-map only.
  • Does not select measures or targets — route to /balanced-scorecard:select-measures and /balanced-scorecard:set-targets-and-initiatives.
  • Does not decide hybrid top perspective for the user — runs pressure test and surfaces trade-offs; strategist chooses.
  • Does not replace practice-setup — reads practice profile; run /balanced-scorecard:practice-setup if profile is empty.

Preconditions

Input If missing
Practice profile and org profile Read if present; if sector unknown, ask before applying checklist
Sector / mission constraint awareness Ask — do not default to for-profit Financial-at-top
User confirmation on ambiguous hybrid Flag [review]; do not fake a single top when pressure test is unresolved

Provisional mode

When sector is unclear or user has not answered pressure test:

  • Label CONFIDENCE: structured first pass.
  • Present checklist options with [review] on unresolved hybrid.
  • Do not proceed to build-strategy-map handoff without stated top perspective or explicit dual-track flag.

Trust spine

  • Confidence bands (structured-aggregation):
    • High: Sector confirmed, top perspective chosen via checklist or documented pressure-test answer, every perspective has stated causal role.
    • Medium: Mostly complete; weak rename rationale or fifth-perspective proposal under review.
    • Low: Scaffold only — sector unknown or hybrid unresolved; dual-track flagged explicitly.
  • Tag vocabulary: [review] on subjective structural choices; [verify] on user-stated sector facts.
  • Failure modes:
    • Strategic advice vs. support: Surfaces checklist and pressure test; does not pick Financial vs Mission for hybrid orgs without user answer.
    • Client confidentiality: Perspective choices may reveal org strategy — apply CONFIDENTIAL header when appropriate.
    • Accountability gap: TOP-PERSPECTIVE DECISION block forces explicit rationale; unresolved hybrid → dual-track note, not silent default.
    • Analytical Rigor: N/A — structural framing, not MECE analysis.
    • Incentive Gaming: N/A — no scoring or tracking.
  • Escalation triggers:
    • Hybrid org with no pressure-test answer → ask test; flag dual-track if genuinely cannot choose.
    • Fifth perspective proposed → run gate; default resist unless user articulates trade-off.
    • Mission-driven org with Financial-at-top requested without rationale → flag [review], cite checklist.
    • Cosmetic renames without causal role → reject rename or require causal-clarity rationale.

Read the full file on GitHub · 186 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. 8d ago First seen · 186 lines · 53 tokens per session scan A a1ec62a6a1dc

Subscribe to this mod's changes

define-perspectives is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 2,049 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

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

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

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