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/richfrem/agent-plugins-skills/github-issue-agentnpx skills add richfrem/agent-plugins-skills --skill github-issue-agentgit clone --depth 1 https://github.com/richfrem/agent-plugins-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/richfrem/agent-plugins-skills/github-issue-agent)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/github-issue-agent"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/github-issue-agent.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 | $0.00080 | $0.01366 |
| Opus 5 | $0.00040 | $0.00683 |
| Sonnet 5 | $0.00016 | $0.00273 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
github-issue-agent 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Agent (github-issue-agent)
Routing Directive: USE ONLY for durable repository bugs, execution friction (T1-T3), map debt, and architectural improvements. DO NOT USE for temporary intra-session checklists (use
task-agentinstead).
The github-issue-agent skill provides a safe, standardized interface for querying, searching, creating, commenting on, and validating GitHub Issues stemming from agent execution friction, map debt, bugs, and system improvements.
Dry-Run Default Execution Contract
[!IMPORTANT] Safety First: By default, all issue-modifying operations (issue creation, commenting, label edits) execute in dry-run / payload-generation mode (
execute=False). No live mutation occurs unlessexecute=Trueis explicitly passed and all safety gates pass.
Before any GitHub issue is created or updated, the request passes through three mandatory security and quality gates:
- Secret Redaction Gate (
redaction_gate.py): Scans titles and bodies for tokens, API keys, private keys, or credentials. Blocks execution if detected. - Taxonomy Validation Gate (
gh_issue_taxonomy_validate.py): Enforcesissue-taxonomy.jsonconstraints. Requirestype:*,tier:*,source:*,risk:*, AND location (area:*ORplugin:*). - Evidence Quality Body Validation Gate (
body_validator.py): Requires standard structured markdown sections (## Summary,## Observed Behavior,## Expected Behavior,## Evidence,## Impact).
Operation Catalog
1. create-friction-issue
Scaffolds and submits (or outputs payload for) a friction issue resulting from agent execution friction or tool failure.
- Helper Script:
plugins/dev-utils/skills/github-issue-agent/scripts/gh_issue_create.py - Default Labels Required:
type:friction,tier:1-friction(ortier:2-structural/tier:3-architecture),source:agent,risk:low(or appropriate risk level), plus location (area:*orplugin:*). - Input Parameters:
title: Short, clear summary of root-cause friction.body: Markdown content conforming to required sections.labels: List of taxonomy labels matchingissue-taxonomy.json.execute: Boolean (Falsefor dry-run payload generation,Truefor live creation viagh).
What ships with it
23 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.
- evals/evals.json 851 B
- issue-taxonomy.json 1.3 KB
- issue-taxonomy.md 1.9 KB
- scripts/body_validator.py 34 B runs code
- scripts/friction_cluster_agent.py 42 B runs code
- scripts/gh_issue_close.py 34 B runs code
- scripts/gh_issue_comment.py 36 B runs code
- scripts/gh_issue_create.py 35 B runs code
- scripts/gh_issue_search.py 35 B runs code
- scripts/gh_issue_taxonomy_validate.py 46 B runs code
- scripts/redaction_gate.py 34 B runs code
- templates/bug-issue.md 332 B
- templates/doc-gap-issue.md 455 B
- templates/enhancement-issue.md 381 B
- templates/friction-issue.md 473 B
- templates/map-debt-issue.md 448 B
- tests/test_dedup_search.py 2.5 KB runs code
- tests/test_friction_cluster.py 1.5 KB runs code
- tests/test_gh_issue_close.py 2.6 KB runs code
- tests/test_gh_mocked_cli.py 6.3 KB runs code
- tests/test_issue_body_rendering.py 1.6 KB runs code
- tests/test_issue_taxonomy.py 1.6 KB runs code
- tests/test_secret_redaction.py 1.9 KB runs code
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 · 101 lines · 80 tokens per session scan A 3ff0e92947ad
github-issue-agent is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,366 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 2026-09-03.
Other skills, from other repositories
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
attio-interaction
Generic Attio CRM REST API v2 recipes for querying records, upserting companies/people/deals, writing notes/tasks/comments, managing lists, and handling webhooks.
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
user-management
How to manage the user registry — creating users for new Slack/GitHub/GitLab/Linear identities, managing aliases, resolving users across platforms. Use when a new human interacts with the swarm or when user identity needs updating.
scheduled-task-resilience
Guardrails for polling, scheduled jobs, and long-running external operations. Use whenever a task waits on CI, builds, deploys, browser jobs, or another asynchronous API so work survives heartbeat checks without duplicate delivery.