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/forbotsake/forbotsake/benchmarknpx skills add forbotsake/forbotsake --skill benchmarkgit clone --depth 1 https://github.com/forbotsake/forbotsakeWhat 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 | $0.00000 | $0.00025 |
| Opus 5 | $0.00000 | $0.00013 |
| Sonnet 5 | $0.00000 | $0.00005 |
| Haiku 4.5 | $0.00000 | $0.00003 |
Grade A, and why
benchmark 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.
What it actually says
/Users/hansel/conductor/repos/forbotsake/.claude/skills/gstack/benchmark/SKILL.md
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 · 1 lines · 0 tokens per session scan A 64be50e7d408
benchmark is a skill published in the GitHub repository forbotsake/forbotsake (5 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 25 tokens. 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
inbox-digest
Scan the last 48 hours of unread newsletters, news emails, and blog digests. Summarize what's relevant to your work. Trigger when the user asks "what did I miss", "any interesting newsletters", or as part of the morning briefing ritual.
meeting-prep
Build a pre-meeting briefing — who's in the room, what they care about, your goal, and the questions to ask. Trigger when the user asks to prep for a meeting or call, "what should I know before", or names an upcoming meeting.
account-health
Score a customer's health, start the renewal motion, and flag churn or expansion early. Trigger when the user asks "how's this account doing", "health check", "are we at risk of churn", "is this account ready to expand", or before a renewal or QBR.
churn-save
Turn a red/amber account into a recovery play — the real risk, the re-engagement outreach, the renewal-clock timing. Trigger when account-health flags a 🔴/🟡 account, when the user says "save this account", "they're going to churn", "the customer went quiet", "renewal at risk", or right after a RETENTION-RISK line is…
retention-feedback
Turn what customer success hears after the sale into product and retention actions. Trigger when an onboarding note, QBR, support thread, or usage review surfaces adoption friction, a churn-risk signal, a feature request that blocks expansion, or a customer who's ready to grow — or when the user says "log this for…
calendar-followup
Surface unfinished follow-ups from last week's external meetings. Trigger when the user asks "who do I need to follow up with", "what meetings haven't I followed up on", or as part of the morning briefing ritual.