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 jon-devlapaz/tink-skills --skill triage-issues-with-jevgit clone --depth 1 https://github.com/jon-devlapaz/tink-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/jon-devlapaz/tink-skills/triage-issues-with-jev)<a href="https://agentmods.dev/skills/jon-devlapaz/tink-skills/triage-issues-with-jev"><img src="https://agentmods.dev/badge/skills/jon-devlapaz/tink-skills/triage-issues-with-jev/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/jon-devlapaz/tink-skills/triage-issues-with-jev"><img src="https://agentmods.dev/badge/skills/jon-devlapaz/tink-skills/triage-issues-with-jev.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 | $0.00072 | $0.02193 |
| Opus 5.5 | $0.00029 | $0.00877 |
| Sonnet 5.5 | $0.00014 | $0.00439 |
| Haiku 4.5 | $0.00007 | $0.00219 |
Grade A, and why
triage-issues-with-jev 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 1mo 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage issues with Jev
Produce a read-only triage report. Jev answers yes/no questions. Ordinary code combines the probabilities and applies the policy in scripts/triage_kernel.py. Jev does not reproduce bugs, write briefs, or change GitHub.
Issues the user authored are in scope. Do not skip them because the author and the maintainer are the same person.
Authority
Default is read-only. These requests do not grant writes: triage, clean up, organize, dedupe, "make sense of the backlog."
A write (comment, label, close, or retitle) happens only when this same request explicitly grants that authority, for example "I grant write authority", "you may comment on these issues", or "close issue 12". Run:
python3 skills/triage-issues-with-jev/scripts/triage_kernel.py authority
with stdin {"request": "<the user message>"}. If writes_authorized is false, stop after the report. If it is true, perform only the granted actions, after the report exists, and show each payload before sending it. Never treat a cleanup request as a grant.
What is not Jev
- Reproduction. A failing test or a checked-out pull request is a later step for an
ACCEPT_CANDIDATEbug. Do not ask Jev whether the bug is real. - Brief writing. Jev does not generate prose. If the user wants a brief, write it with a generative model only after the disposition is already on screen, and only if they asked.
- GitHub writes. Listing and reading issues is allowed. Comments, labels, closes, and retitles are the authority step above.
Do not call Happier companion skills. Do not require Happier stage or needs labels. Do not require an .out-of-scope/ directory. If that directory exists, its markdown files are policy text for the out-of-scope question and nothing else.
Model
Send "model": "jev-1.13.0". Thresholds in the kernel were set while jev-latest resolved to that id. If the response model field is anything else, stop and do not apply the cuts. Read TYPESAFE_API_KEY from the environment at call time. Do not print it, log it, or write it into the repo, the report, or a prompt file.
What ships with it
2 files 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.
- 1mo ago First seen · 182 lines · 72 tokens per session scan A a85d830e6b48
triage-issues-with-jev is a skill published in the GitHub repository jon-devlapaz/tink-skills (16 stars, last pushed 14d ago), licensed MIT. It adds 72 tokens to every session and 2,193 once invoked, about $0.0003 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 2026-09-25.
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.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
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…