Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/sequence.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/commands/bredmond1019/claude-sdk-rs/sequence)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/sequence"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sequence/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/commands/bredmond1019/claude-sdk-rs/sequence"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sequence.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 | $0.00000 | $0.05260 |
| Opus 5.5 | $0.00000 | $0.02104 |
| Sonnet 5.5 | $0.00000 | $0.01052 |
| Haiku 4.5 | $0.00000 | $0.00526 |
Grade A, and why
sequence scanned grade A 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
OK `curl -s localhost:8080/api/runs/<id> | jq .status` returns "aborted" within 5s How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sequence — Cut a verified seam map into an ordered set of blocks each of which ships something.
Stage 3 of the pre-plan pipeline: /assess → /seams → /sequence → /plan.
Method: docs/how-to-plan-with-agents.md in the brain repo.
Variables
$ARGUMENTS — the slug, plus optional flags. Example: orchestration-extensions
| Flag | What it does |
|---|---|
--single-repo |
The work lands in one repo; skip the ownership split and hand off to /plan |
--no-redteam |
Skip the adversarial pass. Do not use before authoring a real plan |
Purpose
Turn seams.md into the cut: an ordered set of candidate blocks, each with an owning repo,
each shipping something the operator can use on its own, sequenced by dependency and by what
makes later work verifiable.
Output: planning/<slug>/sequence.md. It is the only input /plan (one repo) or
/generate-roadmap (multiple repos) needs.
This stage does not author block records or register state.json. That is /plan.
Instructions
-
Read
planning/<slug>/seams.md,assessment.md,verification.md,CLAUDE.md, and the in-scope repos'planning/context.md. Ifseams.mdis missing, stop and point at/seams— sequencing from an assessment alone produces a cut along architectural layers, which is the failure mode this whole pipeline exists to avoid. -
Resolve the forks first. Every fork in
seams.mdmust have an answer before cutting — the cut depends on them. Present them to the user with your recommendations and get a decision. Record each answer and its date insequence.md. This is a blocking gate: an unresolved fork silently becomes a decision made by whichever agent hits it first. -
Cut by deliverable, not by layer. The governing constraint:
Every block ships something the operator can use the day it lands.
This deliberately rules out the natural engineering cut (all the plumbing, then all the value). Test every candidate block against it: "what can the operator do on the day this merges that they could not do the day before?" If the answer is "nothing yet," the block is mis-cut — re-cut it so it lands with a visible surface, however small (a command that prints a plan, one gate that actually fires, a report you can read in the morning).
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.
- 11d ago First seen · 381 lines · 0 tokens per session scan A 40efaee13190
sequence is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,260 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
sequence compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sequencebredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |