dashclaw-retire-legacy

A staged process for retiring the published dashclaw/legacy Node.js SDK path. An SDK is a package that lets other programs use a service, and a major version is a release allowed to include breaking changes.

In plain words
What is it for?
Finding references to the legacy SDK, adding deprecation notices and documentation, and later removing it as a planned major-version change.
Why use it?
It avoids silently breaking users who still import the old package path. The path keeps working while users are warned, then is removed in version 5.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/ucsandman/dashclaw/dashclaw-retire-legacy
Clone the repo
git clone --depth 1 https://github.com/ucsandman/DashClaw

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,509 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.01509
Opus 5 $0.00021 $0.00754
Sonnet 5 $0.00008 $0.00302
Haiku 4.5 $0.00004 $0.00151

Measured yesterday against content hash f42e6865cc77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashclaw-retire-legacy 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 yesterday.

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.

.claude/commands/dashclaw-retire-legacy.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal: retire the legacy SDK without breaking anyone

dashclaw/legacy is a published npm subpath (./legacy in sdk/package.json exports + files; it ships in the tarball). External integrations can import 'dashclaw/legacy' today, so it cannot be silently deleted — every release republishes the npm package at the unified version, so a delete would land in the next patch and break those users with no major signal. Retirement is therefore two milestones:

  • deprecate (now, default) — announce the retirement, keep it working.
  • remove (later, at the v5 major) — delete it as a breaking change.

$ARGUMENTS selects the phase (default deprecate). This command authorizes the Workflow tool (legacy-sdk-deprecation-sweep, mode = the phase).


Phase: deprecate (run this now)

  1. Run the workflow in deprecate mode: Workflow({ name: "legacy-sdk-deprecation-sweep", args: { mode: "deprecate", removalVersion: "5.0.0" } }). It audits every live dashclaw/legacy reference, then in parallel: adds a one-time runtime deprecation console.warn (opt-out via DASHCLAW_SUPPRESS_LEGACY_WARNING=1) + @deprecated, marks every doc/parity surface "removed in v5.0.0", reconciles the drifting method counts (178/187/224), repoints the doc example onto canonical, edits the reference sources (not mirrors), closes the .organism split-the-file backlog, and adds a CHANGELOG ### Deprecated entry.

  2. Trust nothing — re-read the diffs. Confirm the deprecation markers landed AND, critically, that sdk/legacy/ and the ./legacy export + files entry are UNTOUCHED — deprecate must not remove the published contract. A console.warn is the only behavior change to the legacy code itself.

  3. Prove the export still works: npm pack --dry-run (inside sdk/) must still list legacy/dashclaw-v1.js + legacy/index-v1.cjs, and the two legacy regression tests must still pass (a console.warn doesn't fail them).

  4. Mirror the reference sources: npm run bundles:refresh (the deprecation edits touched public/downloads/dashclaw-governance/references/*.md), then git status to see what propagated.

Read the full file on GitHub · 62 lines

Changes

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.

  1. yesterday First seen · 62 lines · 42 tokens per session scan A f42e6865cc77

Subscribe to this mod's changes

dashclaw-retire-legacy is a command published in the GitHub repository ucsandman/DashClaw (296 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 1,509 once invoked, about $0.0002 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 2026-08-30.