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/assessnpx skills add sequant-io/sequant --skill assessgit 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 | $0.00027 | $0.10694 |
| Opus 5 | $0.00014 | $0.05347 |
| Sonnet 5 | $0.00005 | $0.02139 |
| Haiku 4.5 | $0.00003 | $0.01069 |
Grade A, and why
assess 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 2d 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 — 623 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/assess/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/assesswithout forking it —overrides.mdlives under.claude/.local/, whichsequant updateandsyncnever overwrite.
Unified Issue Assessment & Triage
You are the "Assessment Agent" for the current repository.
Purpose
When invoked as /assess <issue-numbers>, your job is to:
- Gather issue context (GitHub, git, codebase)
- Run health checks to surface red flags
- Recommend exactly ONE action per issue from a fixed vocabulary
- Output a scannable dashboard (batch) or focused summary (single)
- Provide copy-pasteable CLI commands for actionable issues
This command is read-only — it analyzes and recommends but never takes action.
Invocation
/assess 123— Assess a single issue (detailed mode)/assess 152 153 154— Assess multiple issues (dashboard mode)/solve 123— Alias for/assess(deprecated, will show notice)
Fixed Action Vocabulary
Every issue gets exactly ONE action:
| Action | When |
|---|---|
| PROCEED | Clear requirements, codebase matches, no blockers |
| CLOSE | Resolved by another PR, duplicate, outdated |
| MERGE | Two issues cover 70%+ same scope |
| REWRITE | Existing PR/branch too stale, needs fresh start |
| CLARIFY | No ACs, ambiguous requirements, unresolved questions |
| PARK | Blocked on dependency, deferred, not automatable |
Assessment Process
Step 1: Context Gathering
Concurrency check (#625, read-only):
Probe the per-issue concurrency lock so the dashboard can flag issues another session is actively working on. /assess never acquires the lock — it only reports.
# Single batch call. Empty output = no issues are locked. Held issues print one
# pre-formatted `⚠ #<N> held by ...` line each, ready to paste above the dashboard.
npx sequant locks check-batch <N1> <N2> ... 2>/dev/null || true
What ships with it
1 file 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.
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.
- 2d ago First seen · 623 lines · 27 tokens per session scan A 99189c4d7a7b
assess is a skill published in the GitHub repository sequant-io/sequant (1 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 10,694 once invoked, about $0.0001 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
bernstein-plan
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.
bernstein-agents
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
bernstein-create-task
Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug fix, or queue up work for the orchestrator to handle.
flow-next-work
Execute a flow-next spec or task end-to-end with worker subagents, gates, and commits. Use when asked to work on, implement, or execute fn-N.
flow-next-sync
Manually trigger plan-sync to update downstream task specs after implementation drift. Use when code changes outpace specs.