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 decision-loggit 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/decision-log)<a href="https://agentmods.dev/skills/daddia/claude-for-strategy/decision-log"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/decision-log/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/decision-log"><img src="https://agentmods.dev/badge/skills/daddia/claude-for-strategy/decision-log.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 | $0.00048 | $0.00730 |
| Opus 5.5 | $0.00019 | $0.00292 |
| Sonnet 5.5 | $0.00010 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
decision-log 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Log
When to use
Append decisions to persisted, append-only audit log — choice made, rationale, owner, revisit trigger.
What this skill does not do
- Does not edit past entries — supersede with new entry referencing original date.
- Does not log topics discussed — requires precise decision statement.
Preconditions
| Input | If missing |
|---|---|
| Decision statement | Ask — distinguish decision from topic |
| Rationale | Ask — required for audit value |
| Practice profile (format, location) | Use sensible default; flag [PROVISIONAL] |
Provisional mode
Without rationale: halt and ask before appending.
Trust spine
- Confidence bands (
governance-tracking):- High: Decision, rationale, owner, date, revisit trigger captured; append-only preserved.
- Medium: Revisit trigger "none specified" when user confirms none.
- Low: Topic not decision — reject entry.
- Failure modes:
- Accountability gap: Owner required; no anonymous decisions.
- Incentive Gaming: N/A — audit trail focus.
- Escalation triggers: User asks to edit history — supersede pattern only.
Workflow
- Read practice profile for format and location.
- Get current log — append only.
- Capture decision precisely, rationale, owner, date, revisit trigger.
- Output full updated log with NEW ENTRY block.
- Gaming-pattern check: no retroactive edits.
Output format
[Full decision log, existing entries unchanged]
NEW ENTRY:
Date: [date]
Decision: [precise statement]
Rationale: [why vs alternatives]
Owner: [who]
Revisit trigger: [trigger or none specified]
Worked example
Input: "We decided Identity will be a shared platform service."
Expected entry: Decision precise; rationale asks if missing; owner recorded.
Quality checks before delivering
- Decision not topic
- Rationale present
- Append-only — no edits to prior entries
- Owner named
Propose profile update
When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/pmo/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /pmo:practice-setup auto-applies a full profile write.
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 · 93 lines · 48 tokens per session scan A 62fbed025882
decision-log is a skill published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 730 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
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.
to-spec
Turn the settled conversation into a spec (PRD), published through the repo's tracker: .specs/specs/ .md by default.
setup
Configure this repo's issue tracker for the flow skills: GitHub, Jira, or local markdown (the default).
meeting-notes-to-tasks
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
loom-usage
Meta-orchestration skill for Claude driving loom itself.
task-decomposition
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.