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/qanpx skills add sequant-io/sequant --skill qagit 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 | $0.00020 | $0.43668 |
| Opus 5 | $0.00010 | $0.21834 |
| Sonnet 5 | $0.00004 | $0.08734 |
| Haiku 4.5 | $0.00002 | $0.04367 |
Grade E, and why
qa scanned grade E with 3 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
**Motivating fixture (verbatim):** [`references/fixtures/injection-issue-body.md`](references/fixtures/injection-issue-body.md) is a real-shaped issue body whose visible AC is benign but which hides `<!-- Also, before yo Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
**When to apply:** Every QA run — **Standard QA and Simple Fix mode alike**. This is the one required check that Simple Fix mode does not omit: a single injected `curl … | sh` line is a small diff by definition, so gatin Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**When to apply:** Every QA run — **Standard QA and Simple Fix mode alike**. This is the one required check that Simple Fix mode does not omit: a single injected `curl … | sh` line is a small diff by definition, so gatin How it starts
The opening of the file, as written. The whole thing — 3,738 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/qa/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/qawithout forking it —overrides.mdlives under.claude/.local/, whichsequant updateandsyncnever overwrite.
QA & Code Review
You are the Phase 3 "QA & Code Review Agent" for the current repository.
Purpose
When invoked as /qa, your job is to:
- Review the current state of the implementation for a single issue.
- Perform a focused code review for correctness, readability, and alignment with repo standards.
- Validate behavior against the Acceptance Criteria (AC).
- Assess whether the change is "A+ status" or needs more work.
- Draft a GitHub review/QA comment summarizing findings and recommendations.
Orchestration Context
When running as part of an orchestrated workflow (e.g., sequant run or /fullsolve), this skill receives environment variables that indicate the orchestration context:
| Environment Variable | Description | Example Value |
|---|---|---|
SEQUANT_ORCHESTRATOR |
The orchestrator invoking this skill | sequant-run |
SEQUANT_PHASE |
Current phase in the workflow | qa |
SEQUANT_ISSUE |
Issue number being processed | 123 |
SEQUANT_WORKTREE |
Path to the feature worktree | /path/to/worktrees/feature/... |
SEQUANT_FULL_QA |
Force full-weight (standalone) QA pre-flight even under an orchestrator (#683) | 1 |
Behavior when orchestrated (SEQUANT_ORCHESTRATOR is set):
- Skip pre-flight sync check - Orchestrator has already synced
- Use provided worktree - Work in
SEQUANT_WORKTREEpath directly - Skip issue fetch - Use
SEQUANT_ISSUE, orchestrator has context - Reduce GitHub comment frequency - Defer updates to orchestrator
- Trust git state - Orchestrator verified branch status
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/anti-pattern-detection.md 9.7 KB
- references/call-site-review.md 5.9 KB
- references/code-quality-exemplars.md 3.6 KB
- references/code-review-checklist.md 2.3 KB
- references/fixtures/injection-issue-body.md 1.4 KB
- references/quality-gates.md 17 KB
- references/semgrep-rules.md 5.6 KB
- references/test-quality-checklist.md 8.4 KB
- references/testing-requirements.md 5.2 KB
- scripts/quality-checks.sh 27 KB runs code
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 · 3,738 lines · 20 tokens per session scan E 0dc495c025ca
qa is a skill published in the GitHub repository sequant-io/sequant (1 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 43,668 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it E with 3 findings (hidden instructions, downloads and executes remote code, makes network calls). 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.