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 performance-narrativegit 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/performance-narrative)<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/performance-narrative"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/performance-narrative/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/performance-narrative"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/performance-narrative.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 | $0.01065 |
| Opus 5.5 | $0.00023 | $0.00426 |
| Sonnet 5.5 | $0.00011 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
performance-narrative 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Narrative
When to use
Turn metrics/tracker results into BLUF narrative for the audience in the practice profile — bottom line first, not metric-by-metric walkthrough.
What this skill does not do
- Does not invent actuals — flag missing numbers
[verify]. - Does not build trackers — route to
/performance:tracker-builder. - Does not replace finance sign-off — board numbers need finance validation per profile gates.
Preconditions
| Input | If missing |
|---|---|
| Metrics or tracker results | Ask user to provide |
| Practice profile (audience, cadence) | Use org default audiences; tag [PROVISIONAL] |
| Headline-worthy context | Ask what audience will act on |
Provisional mode
Without audience in profile: default to sponsor/exec; tag [PROVISIONAL]; apply quiet mode for external-facing per plugin CLAUDE.md.
Trust spine
- Confidence bands (
narrative-synthesis):- High: BLUF headline, 2–4 MECE supporting points, explicit what's-needed, sourced figures.
- Medium: Some unsourced movements tagged
[verify]. - Low: Numbers missing for headline claim — halt or narrow scope.
- Failure modes:
- Strategic advice vs. support: Narrative surfaces findings; audience decides action.
- Client confidentiality: Board/sponsor content — CONFIDENTIAL header; quiet mode for external.
- Accountability gap: What's-needed stated explicitly, not inferred.
- Analytical Rigor: MECE supporting points; so-what test on each metric.
- Incentive Gaming: N/A — narrative shape.
- Escalation triggers: Headline depends on unverified figure — tag before BLUF.
Workflow
- Read practice profile for audience and cadence.
- Identify headline — one thing audience must know this period.
- Write bottom line first — conclusion not topic.
- Group supporting metrics into 2–4 MECE points; so-what test.
- State what's needed — decision, investment, awareness.
- Full metric detail last as reference appendix.
- Connector figures. When metrics are read from
~~bi analytics,~~spreadsheet,~~crm, or other MCP sources, tag each number[sourced: <connector>, <dataset/report>, <as-of date>]per../../references/trust-conventions.md. Uncited connector figures are not allowed in board-facing output; use[verify]orINPUT NEEDEDwhen the pull fails. - MECE/falsifiability check before output.
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 · 109 lines · 57 tokens per session scan A 1c648d6ece70
performance-narrative 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 1,065 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 2026-09-03.
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.