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 glassity/agent-skills --skill opp-triagegit clone --depth 1 https://github.com/glassity/agent-skillsWrote 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/glassity/agent-skills/opp-triage)<a href="https://agentmods.dev/skills/glassity/agent-skills/opp-triage"><img src="https://agentmods.dev/badge/skills/glassity/agent-skills/opp-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/glassity/agent-skills/opp-triage"><img src="https://agentmods.dev/badge/skills/glassity/agent-skills/opp-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 | $0.00078 | $0.00928 |
| Opus 5 | $0.00039 | $0.00464 |
| Sonnet 5 | $0.00016 | $0.00186 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
opp-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 10d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opportunity triage — mutations, two-phase
When to use
- "Move this assignment to execution", "archive this assignment"
- "Approve the execution plan for opp X"
- "Reassign this assignment to service S"
Use opp-list or opp-show first if the user has not named the record.
Binary check
Run command -v glassity before the first CLI call. If it is missing, stop and
tell the user to install it with brew install glassity/tap/glassity or from
https://github.com/glassity/cli/releases. No account yet? Sign up at
app.glassity.cloud.
The rule that makes this safe
The binary gates every mutation behind two phases. Phase 1 makes no network call: it renders the exact PATCH or POST it would send — method, path, headers with the token redacted, and the canonical JSON body — and issues an HMAC-bound confirm token. Phase 2 redeems that token and puts those same bytes on the wire. Change anything between the phases and phase 2 refuses to send.
After running phase 1 you must:
- Show the user the full plan from stderr, verbatim. Do not summarise it. The point is that they read the bytes that will be sent.
- Ask explicitly: "Approve this mutation? (yes/no)"
- Only run phase 2, with
--confirm-token=<token>, after an affirmative reply in the same turn.
Do not run phase 1 and phase 2 in one bash invocation. Do not add any of these commands to an always-allow rule. The binary refuses to redeem a token less than 1.5 seconds after issuing it, but that is a backstop; the defence is the person reading the plan.
Phase 1 — issue the token, no network call
glassity --output=json opp transition <assignment-id> --target-state <state> [--comment "..."]
glassity --output=json opp approve <opportunity-id>
glassity --output=json opp assign <assignment-id> --service-id <service-id>
glassity --output=json opp pipeline-move <opportunity-id> --target-stage <stage> [--comment "..."]
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.
- 10d ago First seen · 84 lines · 78 tokens per session scan A ef8b95ad4bda
opp-triage is a skill published in the GitHub repository glassity/agent-skills (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 78 tokens to every session and 928 once invoked, about $0.0004 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
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.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.