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/daddia/claude-for-strategy/practice-setupnpx skills add daddia/claude-for-strategy --skill practice-setupgit clone --depth 1 https://github.com/daddia/claude-for-strategyWrote 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/daddia/claude-for-strategy/practice-setup)<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/practice-setup"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/practice-setup.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 5.1 | $0.00092 | $0.01668 |
| Opus 5 | $0.00046 | $0.00834 |
| Sonnet 5 | $0.00018 | $0.00334 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
practice-setup 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 5d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Practice Setup — balanced-scorecard
When to use
For strategy office, FP&A, or ops excellence leads configuring the balanced-scorecard plugin for the first time or after material change to sector model, perspective set, cadence, or cascade policy. Explicit invocation only (disable-model-invocation: true).
Sector determines the perspective set — get it right before anything else.
What this skill does not do
- Does not run BSC analysis skills — sets up profiles that other skills read; does not build maps, measures, or scorecards during setup.
- Does not auto-write without confirmation — shows summary, waits for explicit yes, then writes.
- Does not modify other plugins' profiles — writes
org-profile.md(shared) andbalanced-scorecard/CLAUDE.mdonly. - Does not replace propose profile update — other skills must show diffs and ask before profile changes.
Preconditions
| Input | If missing |
|---|---|
| User intent (quick / full / redo / check-integrations / resume) | Detect existing setup per framework; offer quick vs full if unspecified |
Write access to ~/.claude/plugins/config/claude-for-strategy/ |
Explain path; create parent dirs on confirmed write |
For --resume: practice-setup-resume.json |
Report no session; offer fresh start |
Provisional mode
When user chooses --quick or org profile already complete:
- Skip org questions already answered in
org-profile.md. - Use sensible defaults for non-essential plugin fields; label defaults explicitly in summary (
[default — change on redo]). - Do not mark
Status: completewith major blanks — use "see org profile" or "no strong preference" per framework.
Trust spine
- Confidence bands (
structured-aggregation):- High: Org + plugin summaries confirmed; sector and top perspective explicit; seed documents reviewed in full mode.
- Medium: Quick mode with labeled defaults; some plugin fields deferred.
- Low: Interview paused mid-way — resume file written; no profile write until resumed and confirmed.
- Tag vocabulary:
[review]on ambiguous sector/top-perspective choices;[verify]on user-stated facts before writing to profile. - Failure modes:
- Strategic advice vs. support: Captures user's stated conventions; does not recommend perspective model — pressure-test questions only, strategist decides.
- Client confidentiality: Profiles may contain proprietary org facts — remind user where files are stored; no paste into chat beyond summary.
- Accountability gap: Summary shown before write; user must confirm explicitly — no silent profile updates.
- Analytical Rigor: N/A — setup skill, not analysis.
- Incentive Gaming: N/A — no scoring or tracking.
- Escalation triggers:
- Hybrid sector (dual mission/financial primacy) → document pressure-test answer; flag
[review]if unresolved. - Legacy profile at non-standard path → offer migration; do not delete without confirmation.
- User cannot access seed documents → note gap; continue with interview answers only.
- Install scope blocks file reads → explain user-scoped vs project-scoped per framework.
- Hybrid sector (dual mission/financial primacy) → document pressure-test answer; flag
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.
- 5d ago First seen · 150 lines · 92 tokens per session scan A d21a70d8fb18
practice-setup is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 1,668 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.
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.
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…
spec
Spec-driven development in the active repository's spec/{feature}/ directory. Use when user says /spec, "write a spec", "plan a feature", "create a PRD", "spec status", "spec out this epic", or references spec/ directory. Sizes work from small to epic, where an epic is a parent spec with numbered child specs.…
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…
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…
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…