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/sdd-clinpx skills add danweinerdev/claude-sdd-planner --skill sdd-cligit 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-cli)<a href="https://agentmods.dev/skills/danweinerdev/claude-sdd-planner/sdd-cli"><img src="https://agentmods.dev/badge/skills/danweinerdev/claude-sdd-planner/sdd-cli.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 | $0.00065 | $0.01937 |
| Opus 5 | $0.00032 | $0.00968 |
| Sonnet 5 | $0.00013 | $0.00387 |
| Haiku 4.5 | $0.00006 | $0.00194 |
Grade A, and why
sdd-cli 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 3d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The sdd CLI — Interface Discipline
The sdd binary is the write path for SDD artifacts and the deterministic
half of validation. Artifacts are compiled documents: create and modify them
through the binary, never by hand-editing frontmatter or evidence sections —
a hand edit bypasses schema compilation, digest tracking, and the refusal
gates the workflow depends on.
Run sdd help for the authoritative usage; sdd schema list / sdd schema show <type> for the artifact contracts. This skill carries the discipline
and the task→command map, not every flag.
Start here
Run sdd doctor once when you begin using sdd in a project. It reports the
binary in use, the resolved planning root, and the embedded schema set, and it
regenerates hooks.json when that file is absent or does not match this
plugin version's hook set.
That last part is why it matters: hooks.json is generated per platform, so a
plugin upgrade leaves the previous version's file in place. The events it
declares keep firing, which means a newly added event silently never runs and
nothing looks wrong. doctor is the only thing that compares. Pass --check
to report without repairing.
Contracts (apply to every subcommand)
- Exit codes:
0success ·1refused mutation or authoritative findings ·2malformed invocation or the operation could not run. Exit1means the gate is doing its job — fix the input or complete the missing prerequisite; never work around it by editing the file directly. - Severities follow the compiler model. Only
error(andoperational, meaning a check could not run) makes a root or ledger invalid and sets a failing exit status.warningis a real defect that cannot threaten correctness — including one inherited history forbids repairing;candidateis a signal for a human to judge;waivedis a finding someone explicitly excepted. All three are reported and none gates. A clean run with non-blocking findings still saysValid, with the count — treat "no findings" and "findings, none blocking" as different states. - Machine reads: prefer
--jsonover parsing rendered markdown. - Preview before mutate:
--dry-runand--diffare available on the writing commands; use them when the change is non-obvious. - Concurrent-edit safety:
sdd showreports a content digest; pass it back via--expect DIGESTonapply/section setso the write is refused if the artifact changed underneath you. - stdin writers:
applyreads a full Markdown proposal on stdin;section setreads one section body on stdin and leaves everything else byte-identical (aside fromupdated).
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.
- 3d ago First seen · 117 lines · 65 tokens per session scan A d896df1fd329
sdd-cli is a skill published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,937 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
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
hns-lsel-applier
Local Self-Evolution Loop (LSEL) APPLY engine — the playback-only consumer of approved decision.json records that drives .moai/hooks/lsel-apply.sh for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001 M3). Reads an approved decision.json, validates the target against the frozen allowlist…
moai-workflow-ddd
Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technical debt safely.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
hns-oss-docs-verify
Mandatory verify recipe for the oss-docs harness — the runnable exit gate every specialist executes before returning: warning-free hugo build, sitemap existence, URL-blacklist grep, Mermaid LR/RL direction grep, 4-locale file-existence and section-count parity, README 4-file heading parity, and body-emoji scan. All…
nw-at-completeness-check
Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.