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/joakimcarlsson/bastion/github-issues-labelsnpx skills add JoakimCarlsson/bastion --skill github-issues-labelsgit clone --depth 1 https://github.com/JoakimCarlsson/bastionWrote 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/joakimcarlsson/bastion/github-issues-labels)<a href="https://agentmods.dev/skills/joakimcarlsson/bastion/github-issues-labels"><img src="https://agentmods.dev/badge/skills/joakimcarlsson/bastion/github-issues-labels.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01062 |
| Opus 5 | $0.00037 | $0.00531 |
| Sonnet 5 | $0.00015 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
github-issues-labels 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 4d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issues and Labels
Tools
Use gh for GitHub (issues, labels, milestones, PRs). Use git only for local repo operations. Do not use the web UI for bulk or scripted tasks unless the user asks.
Core Principles
Every issue must leave the codebase in a runnable state
- Never split work so the project is broken mid-series. Each issue is self-contained or extends something already working.
- Always include How to verify (runnable) ÔÇö exact local steps before opening a PR.
- Acceptance criteria must be binary (done or not done).
Every issue must explain why, not just what
- Why ÔÇö motivation, user story, constraint
- What ÔÇö precise scope
- How ÔÇö design decisions, edge cases, contracts
- Done when ÔÇö runnable verification before PR
Issue Body Template
## Why / Context
## What needs to happen
## How it should work
## Acceptance criteria
- [ ] Specific, binary, testable criterion
## How to verify (runnable)
## Dependencies / notes
Labels
Every issue gets at least one label. One value per axis when that axis carries signal.
prefix/value axes
| Prefix | Vocabulary | Question |
|---|---|---|
kind/ |
closed | Type of work |
priority/ |
closed | Urgency + timeframe |
triage/ |
closed | Triage state |
lifecycle/ |
closed | Active vs stale |
area/ |
open ÔÇö from this codebase | Subsystem |
sig/ or team/ |
open ÔÇö from org | Owner team |
kind/: kind/bug, kind/feature, kind/cleanup, kind/refactor, kind/documentation, kind/security, etc. Use kind/feature ÔÇö never bare enhancement.
priority/: priority/critical-urgent, priority/important-soon, priority/important-longterm, priority/backlog, priority/awaiting-more-evidence. Never bare high/medium/low.
triage/: triage/accepted, triage/needs-information, etc.
area/: derive from directory/module boundaries in this repo ÔÇö never copy from another project.
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.
- 4d ago First seen · 133 lines · 74 tokens per session scan A 36f5e4a9c790
github-issues-labels is a skill published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,062 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
trelly-mcp
Configure and use the trelly MCP stdio server (trelloboardslist, trellocardcreate, trellosearch, trelloapiget, etc.). Use when wiring Cursor/Claude MCP, listing or showing Trello cards/todos, linking GitHub PRs/commits, or choosing MCP vs CLI.
trelly
Operate the trelly Trello CLI (npm trelly; bin trelly): auth setup/login, human vs --json output, boards/lists/cards, search, attachments, GitHub PR/commit links on cards, trelly ui, trelly api. Use when the user asks to run trelly commands, list or show Trello cards/todos, link a GitHub PR or commit to a card, or…
seeds-issue-audit
Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".
retro
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.