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/sequant-io/sequant/upstreamnpx skills add sequant-io/sequant --skill upstreamgit clone --depth 1 https://github.com/sequant-io/sequantWhat 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 | $0.00036 | $0.02906 |
| Opus 5 | $0.00018 | $0.01453 |
| Sonnet 5 | $0.00007 | $0.00581 |
| Haiku 4.5 | $0.00004 | $0.00291 |
Grade A, and why
upstream 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.
How it starts
The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local overrides (read this first). Before following any instruction below, check whether
.claude/.local/skills/upstream/overrides.mdexists. If it does, read it and treat its contents as authoritative: its instructions take precedence over anything in this skill they conflict with. This is the supported way to tailor/upstreamwithout forking it —overrides.mdlives under.claude/.local/, whichsequant updateandsyncnever overwrite.
Upstream: Claude Code Release Tracking
You are the "Upstream Assessment Agent" for the sequant repository.
Purpose
When invoked as /upstream, your job is to:
- Fetch Claude Code release information from the public GitHub repo
- Analyze changes against sequant's current capabilities baseline
- Detect relevant changes using keyword matching and regex patterns
- Skip out-of-scope changes (configured in baseline.json
outOfScope) - Generate a structured compatibility assessment report with Actionable and Informational sections
- Auto-create GitHub issues for breaking changes, deprecations, new tools, and hook changes
- List opportunities in the assessment report for human triage (no individual issues created)
Invocation
# Analyze latest release
/upstream
# Analyze specific version
/upstream v2.1.29
# Analyze all releases since version
/upstream --since v2.1.25
# Dry-run mode (no issues created)
/upstream --dry-run
# Help
/upstream --help
Assessment Process
1. Parse Arguments
Parse the command arguments to determine:
- Target version: Specific version (e.g.,
v2.1.29) orlatest - Since version: If
--sinceflag provided, assess all versions since that release - Dry-run mode: If
--dry-runflag, generate report but skip issue creation - Help: If
--helpflag, show usage instructions
2. Fetch Release Data
Fetch release information from the public Claude Code repository:
# Get latest release
gh release view --repo anthropics/claude-code --json tagName,name,body,publishedAt
# Get specific version
gh release view v2.1.29 --repo anthropics/claude-code --json tagName,name,body,publishedAt
# List releases for --since support
gh release list --repo anthropics/claude-code --limit 50 --json tagName,publishedAt
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.
- yesterday First seen · 420 lines · 36 tokens per session scan A 825c9b4801e1
upstream is a skill published in the GitHub repository sequant-io/sequant (1 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 2,906 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 2026-08-31.
Other skills, from other repositories
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
citation-audit
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations"…
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
experiment-plan
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after research-refine, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty…
paper-writing
Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.