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 score-and-retrogit 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/score-and-retro)<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/score-and-retro"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/score-and-retro/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/score-and-retro"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/score-and-retro.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 | $0.00059 | $0.01483 |
| Opus 5 | $0.00030 | $0.00741 |
| Sonnet 5 | $0.00012 | $0.00297 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
score-and-retro 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 11d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score and Retro
When to use
End-of-cycle scoring plus keep/kill/revise — checking whether hitting numbers served the objective, not just grading KRs.
What this skill does not do
- Does not set next-cycle targets — route to
/okr:set-targets. - Does not invent actuals —
INPUT NEEDEDwhen missing. - Does not default objective call to KR average unless profile explicitly requires it.
Preconditions
| Input | If missing |
|---|---|
| Baseline, target, actual per KR | Score INPUT NEEDED — do not guess |
| Org + OKR practice profiles | Use default scoring doctrine; tag [PROVISIONAL — configure profile] |
| Commit/aspirational labels per KR | Ask; do not infer from score |
Provisional mode
[PROVISIONAL — configure profile for org-calibrated scoring] when profiles missing; default formula applies.
Trust spine
- Confidence bands (
governance-tracking):- High: Every KR scored with shown arithmetic; objective calls with divergence checks; sandbagging named if present.
- Medium: Some
INPUT NEEDED; provisional profile scoring. - Low: Actuals missing for majority of KRs — halt retro conclusions.
- Failure modes:
- Strategic advice vs. support: Keep/kill/revise are recommendations; calibration session owns final calls.
- Client confidentiality: Scores may be sensitive — CONFIDENTIAL header.
- Accountability gap: KR/objective divergences flagged, not averaged away.
- Analytical Rigor: N/A — governance shape.
- Incentive Gaming: Guards grade inflation and sandbagging normalization — 1.0 on aspirational or consistent ~1.0 across teams named as pattern.
- Escalation triggers: Widespread sandbagging pattern — flag for calibration, not praise.
Scoring doctrine (inline)
Apply formula from practice profile. If none set, use defaults below.
Default formula — increase-is-better KRs
score = (actual − baseline) ÷ (target − baseline)
Cap at 1.0 unless profile allows overachievement. Below baseline → 0.0.
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.
- 11d ago First seen · 166 lines · 59 tokens per session scan A b3cf8cdf8ce3
score-and-retro is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,483 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.
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…
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…
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…