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 select-measuresgit 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/select-measures)<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/select-measures"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/select-measures/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/select-measures"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/select-measures.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 | $0.00057 | $0.01511 |
| Opus 5.5 | $0.00023 | $0.00604 |
| Sonnet 5.5 | $0.00011 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
select-measures 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Select Measures
When to use
For strategy office or FP&A practitioners assigning measures to strategy-map objectives. The discipline most scorecards skip: explicit lead/lag classification per measure and a portfolio mix check per perspective — not just attaching a number to each objective.
What this skill does not do
- Does not build the strategy map — requires
build-strategy-mapobjectives as input. - Does not set targets or initiatives — route to
/balanced-scorecard:set-targets-and-initiatives. - Does not own formal metric definitions when
performanceis installed — hands off to/performance:metrics-glossary(same seam asokr:instrument-metrics). - Does not validate causal mechanisms empirically — that's
/balanced-scorecard:review-and-validate.
Preconditions
| Input | If missing |
|---|---|
| Strategy map with objectives per perspective | Halt — route to build-strategy-map |
| Practice profile measure-count ceiling | Use default ~20–25; tag [PROVISIONAL] |
| Perspective causal roles (from map / define-perspectives) | Read profile; flag [review] if top perspective unclear |
Provisional mode
When objectives exist but measure data sources are unknown:
- Propose measures with formula/source as
TBD — [verify]inline (whenperformancenot installed). - Label borderline lead/lag cases honestly; do not call everything leading.
- Flag over-3-measures-per-objective as objective-too-broad, not measure sprawl.
Trust spine
- Confidence bands (
structured-aggregation):- High: Every objective has 1–3 measures, lead/lag classified, mix check per perspective, total within ceiling.
- Medium: Mostly complete; some sources TBD or borderline classifications flagged.
- Low: Scaffold only — missing map input or majority measures without classification.
- Tag vocabulary:
[verify],[review],[PROVISIONAL]on defaults. - Failure modes:
- Strategic advice vs. support: Proposes measure candidates; strategist selects and removes — removal candidates listed, not silently dropped.
- Client confidentiality: Measure definitions may expose operational detail — CONFIDENTIAL header when appropriate.
- Accountability gap: LEAD/LAG MIX CHECK and over-ceiling removal candidates force portfolio judgment; no hidden dilution.
- Analytical Rigor: N/A — classification and completeness, not MECE decomposition.
- Incentive Gaming: N/A — no scoring or status reporting here.
- Escalation triggers:
- More than 3 measures proposed for one objective → flag objective too broad; suggest split in
build-strategy-map. - Top perspective majority leading → flag misaligned with causal role (lagging confirmation expected).
- L&G or Internal Process majority lagging → flag no early-warning system.
- Total count over ceiling → name removal candidates with rationale.
- More than 3 measures proposed for one objective → flag objective too broad; suggest split in
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 · 132 lines · 57 tokens per session scan A 310c28bf8adf
select-measures is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,511 once invoked, about $0.0002 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.