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 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/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.
<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="Reviewed on agentmods" width="80" 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 5.5 | $0.00037 | $0.00667 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,668 once invoked, about $0.0004 per session on Opus 5.5. 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
review
Run the full pre-merge panel: parallel audit and lens reviewers over a diff, consolidated into one severity-ranked verdict.
to-tickets
Slice a spec or a ticket into tracer-bullet tickets with blocking edges, published through the repo's tracker: .specs/tickets/ .md by default.
tdd
Test-driven development, from unit to end-to-end tests. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration or end-to-end tests (Playwright, Cypress). Don't use to backfill tests on existing code (/refactor) or diagnose an unknown bug (/debug).
visual-review
Two visual modes — render a PR diff as an HTML page with each hunk annotated by principle, or check a UI change in a real browser (screenshots, console, network). Use for a visual/HTML diff report, "check the UI", or "screenshot before/after". Don't use for text-only feedback (/code-review), unit tests (/tdd), or full…
to-pr
Gate, push, and open a GitHub pull request on the repo's PR template, then watch CI.
debate
Settle a go/no-go on one risky change against an alternative through an advocate, a skeptic, and a neutral investigator.