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 agentmods add skills/danweinerdev/claude-sdd-planner/decision-lognpx skills add danweinerdev/claude-sdd-planner --skill decision-loggit clone --depth 1 https://github.com/danweinerdev/claude-sdd-plannerWrote 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/danweinerdev/claude-sdd-planner/decision-log)<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/decision-log"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/decision-log.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00642 |
| Opus 5 | $0.00034 | $0.00321 |
| Sonnet 5 | $0.00013 | $0.00128 |
| Haiku 4.5 | $0.00007 | $0.00064 |
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 5d 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.
This is a copy
98% identical to sdd-decision-log — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Log — Capture and Collision Discipline
The full convention (entry schema, lifecycle rules, collision procedure, distribution rules) lives in shared/decision-log.md in the plugin directory — read it before your first ledger write of a session. This skill exists so decision moments outside the lifecycle skills still reach the ledger.
Resolve the ledger per shared/decision-log.md § Ledger location — <planning-root>/Decisions/decisions.md for an in-repo planning root, <repo-root>/DECISIONS.md when the planning root is external (decisions live with the repo they represent). Create it from shared/templates/decision-log.md if missing.
When the user just decided something
- Recognize the moment: a stated choice between alternatives, a definition of a project term, an answer to a design question, or an explicit reversal. Then apply the admission test (
shared/decision-log.md§ Capture) before writing anything: the truth has to outlive the document being worked on, not already be carried by that document, and have had a real alternative that lost. Status updates, task events, one-off dispositions, and choices that a spec or design already states in full are not ledger entries — leaving them where they are is the correct outcome, not a miss. - Run the collision check first (
shared/decision-log.md§ Collision Detection): grep the ledger for the new entry's tags, scope, and key nouns; apply the structural checks; judge survivors. Oncontradicts/supersedes→ STOP and present both entries for the user to reconcile. Never auto-resolve, never pick by recency. - Draft the entry (next sequential
D-NNNN,decided_by: useronly if the user actually stated the choice — otherwisestatus: proposed) and show the exact, complete entry text to the user for explicit approval before writing anything. The ledger is never edited without that approval — the decision being the user's does not make the write approved, and non-objection is not approval. If the user amends the entry, show the amended text and get approval again. - Only after explicit approval: append the approved text verbatim, update the ledger's
updateddate, and confirm the frontmatter still parses as YAML. Confirm in one line (e.g., "Recorded as D-0007 in the decision ledger").
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.
- 5d ago First seen · 23 lines · 67 tokens per session scan A 0bf301c2885f
decision-log is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 642 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to sdd-decision-log, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
nw-buddy-ssot-knowledge
Single Source of Truth detection — where truth lives in an nWave repo and how to avoid contradicting it.
half-clone
Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
quarter-clone
Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
debrief
BETA / under development. Mine the current project's Claude Code sessions for recurring corrections, then interrogate them — consolidate clusters into themes, ask a SET of open "why" questions per theme, self-answer the evidence-answerable ones and forward the developer-only ones to the user, record confirmed answers…
memory-audit
Audit Claude's per-user memory for this project and produce a report. Asks at the start whether the user wants a non-technical summary or a full technical audit. Never edits memory — produces a report only. Usage: /memory-audit.