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 skills add gs-bbluhm/gainsight-mcp-plugins --skill staircase-book-triagegit clone --depth 1 https://github.com/gs-bbluhm/gainsight-mcp-pluginsWrote 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/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-book-triage)<a href="https://agentmods.dev/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-book-triage"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-book-triage/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/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-book-triage"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-book-triage.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 | $0.00147 | $0.03589 |
| Opus 5.5 | $0.00059 | $0.01436 |
| Sonnet 5.5 | $0.00029 | $0.00718 |
| Haiku 4.5 | $0.00015 | $0.00359 |
Grade A, and why
staircase-book-triage 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 25d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staircase Book Triage (CSM cockpit)
A CSM opens Monday with a full book and three hours. This skill turns the whole book into one ranked "do this first" list: not a health dashboard, an action queue. It reads every motion at once (risk that's loud, risk that's silent, renewals with a clock, coverage that's one-deep, accounts gone quiet, expansion that's heating) and hands back the few accounts that actually need the CSM this week, each with the one next move.
The architecture (why it's cheap): ONE owner-scoped report pulls the ~14 signal columns for the whole book; every lens below is a client-side filter over that single pull. No per-account calls to build the list; those are reserved for the drill on the few accounts the CSM picks.
This is the single-book lens. For the portfolio/leader view use ../staircase-risk-radar/; for one account's deep read use ../staircase-account-deep-dive/ or ../staircase-risk-check/; to plan renewals specifically use ../staircase-renewal-watchlist/. A manager prepping for a 1:1 with a teammate (personal effort/overwhelmed test + this same book, from the manager's chair) should use ../staircase-1on1-prep/ instead. It reuses this skill's 7-motion table by reference rather than duplicating it.
Foundation references (read BEFORE composing any query)
../staircase-mcp-expert/+../staircase-mcp-expert/references/advanced-report-patterns.md: the report engine, the argument system, owner scoping, field ids, and the reliability rules in../staircase-mcp-expert/references/anti-patterns.md.../staircase-app-design/: the interactive-cockpit standard (see the visual section).../../_shared/staircase-output-best-practices.md: house style, evidence discipline, no CRM writes.- User profile (if present):
~/.staircase-mcp/user-profile.md, the CSM's identity / owner scope.
Scope (decide first)
- Use the resolved book-owner field.
customer.owneris not always the CSM; on some orgs it holds a different role and the real book lives on another field. Readscope.book_owner_fieldfrom~/.staircase-mcp/user-profile.md; if absent, run the foundation's first-call contract (../staircase-mcp-expert/SKILL.mdstep 0, recipescope.membership), which computes it and asks only when ambiguous. Use that field for all scoping below. - Self (the default):
customer.<book_owner_field> In [current_user_id](orEqual <id>for a custom Reference field).current_user_idcomes fromreport_metadataand is exact. This is how the CSM running the skill scopes to their own book. - A named CSM (a manager looking at one rep, or when the profile names someone):
customer.<book_owner_field>.full_name In ["<name>"]inrun_report. A bare name on the Reference field itself errors; go through the.full_nameleaf, or use the person'suser.id. - Portable fields only. Never hardcode a specific
_cfield id. The confirmed book-owner field is a runtime parameter, discovered per org, not baked into this skill.
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.
- 25d ago First seen · 136 lines · 147 tokens per session scan A 6b4a7a799d05
staircase-book-triage is a skill published in the GitHub repository gs-bbluhm/gainsight-mcp-plugins (4 stars, last pushed 20d ago), licensed MIT. It adds 147 tokens to every session and 3,589 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…