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 danweinerdev/claude-sdd-planner --skill sdd-decidegit 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/sdd-decide)<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/sdd-decide"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/sdd-decide.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 | $0.00043 | $0.01664 |
| Opus 5 | $0.00022 | $0.00832 |
| Sonnet 5 | $0.00009 | $0.00333 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade C, and why
sdd-decide scanned grade C with 1 finding 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 2d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
0. An explicit `sdd-decide` is the user asking for the entry — record it. But if the statement plainly fails the admission test (it restates what an artifact already says, or it's an event or one-off disposition), say so Copies of this mod
1 near-identical copy found in the catalogue:
- decide — 91% identical, 19 lines differ
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Ledger
Resources
Before opening shared/..., follow symlinks in this loaded file's path, then derive <plugin-root> from <plugin-root>/skills/<name>/SKILL.md; fallback search roots are repository/user .agents/ (including $HOME/.agents/plugins/*/), Codex ${CODEX_HOME:-$HOME/.codex}/plugins/cache/*/*/*/, and runtime-configured skill roots. Accept only a root containing this skill, shared/agent-runtime.md, and the matching plugin manifest; never use the working directory. Then read <plugin-root>/shared/agent-runtime.md and <plugin-root>/shared/path-resolution.md, and resolve every shared/<path> reference in this skill against <plugin-root>.
Resource boundary: Read the plugin, all SKILL.md files, and shared/ resources in place. Never copy or symlink them into the working directory, target repository, or planning root. Only generated SDD outputs may be materialized from bundled resources.
When to Use
- Explicitly record a decision, concept definition, or answered design question as durable truth — a truth that must be findable without knowing which document to open, not a choice a spec or design already states (
shared/decision-log.md§ Capture, the admission test) - Look up what was decided about a topic ("what did we decide about auth?")
- Reconcile a collision — supersede an old decision with a new one
- Backfill a decision the automatic capture missed
- Audit ledger hygiene (
sdd-decide check) — stale citations, missed collisions, malformed entries
The convention — entry schema, lifecycle rules, collision procedure — is defined in shared/decision-log.md (single source of truth). Read it before operating on the ledger.
Invocation
/decide <statement> # Record a decision (default subcommand)
/decide list [tag|scope] # List entries, optionally filtered
/decide search <term> # Find entries matching a term
/decide show D-NNNN # Show one entry with its body section, if any
/decide accept D-NNNN # Promote a proposed entry to accepted
/decide supersede D-NNNN # Replace an entry with a new decision
/decide check # Hygiene audit of the ledger and its citations
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.
- 2d ago Changed a231793e7a80
- 6d ago First seen · 70 lines · 43 tokens per session scan C df4abbdeff17
sdd-decide is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,664 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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…
brief-me
Print a plain-English re-entry briefing for a user who has lost the thread of a long-running session — after a distraction, overnight, or over a weekend. Re-explains what the session is, where it got to, what state the work is in right now, what Claude is waiting on from the user, and the single next step. Grounds…
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.