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 ehmo/gum --skill gum-haspgit clone --depth 1 https://github.com/ehmo/gumWrote 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/ehmo/gum/gum-hasp)<a href="https://agentmods.dev/skills/ehmo/gum/gum-hasp"><img src="https://agentmods.dev/badge/skills/ehmo/gum/gum-hasp.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.00331 |
| Opus 5 | $0.00008 | $0.00166 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
gum-hasp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
gum + HASP
Use this when gum work also needs local secrets outside Google's OAuth flow.
gum handles Google API discovery, OAuth login, local refresh-token storage, and guarded API calls.
HASP handles repo, test, and deploy secrets for commands and agents.
Start
Install HASP and run setup:
brew tap gethasp/homebrew-tap
brew install hasp
hasp setup
Read HASP at https://github.com/gethasp/hasp before changing secret policy.
Safe Pattern
Register gum OAuth secrets through stdin:
printf '%s' "$GOOGLE_OAUTH_CLIENT_SECRET" \
| gum auth use-oauth-client --client-id "$GOOGLE_OAUTH_CLIENT_ID" --secret-stdin
Put other secrets in HASP, then run gum under a short grant:
hasp secret add
hasp app connect gum-work --cmd 'gum doctor' --install=never
hasp run --project-root . \
--target gum-work \
--grant-project session \
--grant-secret session \
-- gum doctor --format=json
Rules
Keep secret values out of prompts, repo files, shell history, and agent notes.
Use gum for Google API calls. Use HASP for non-Google secrets the command needs. Give agents the narrowest HASP grant that lets the command run.
Run hasp secret diff .env before committing a repo that used to carry plaintext secrets.
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.
- 5d ago First seen · 55 lines · 16 tokens per session scan A bce1fea491c6
gum-hasp is a skill published in the GitHub repository ehmo/gum (32 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 331 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 2026-09-03.
Other skills, from other repositories
migration
A step-by-step guide for upgrading programming languages, frameworks, and libraries while checking for breaking changes. A breaking change is an update that requires existing code to be modified.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
performance
A guide to measuring and improving the speed and resource use of Go programs. It explains benchmarks and profiling, which records where a program spends time or memory.
sabx
Manage SABnzbd queues, history, NZBs, priorities, limits, RSS feeds, schedules, and server state through sabx.
swiftui-expert-skill
Use when writing, reviewing, or refactoring SwiftUI code — state management, view composition, performance, macOS-specific APIs, or iOS 26+ Liquid Glass adoption. Also triggers whenever an Xcode Instruments .trace file is referenced (to analyse it) or the user asks to record a new trace — attach to a running app…
working-with-lacquer
Use when working in a lacquer-managed project (one with a .lacquer.toml) and anything about that management comes up: the drift audit inside the "Detect changed paths" CI job fails, lacquer audit exits 3/4/6, a lint config or CI workflow you edited reverts on the next sync, a hook or workflow needs changing, the…