issue-report-filing-flow

issue-report-filing-flow is a skill for Claude Code, Codex from Lingtai-AI/lingtai. It costs 71 tokens per session (1,761 once invoked), scanned A, original, Apache-2.0.

A guide for deciding how a prepared issue report is sent to GitHub or handed to a person to file. GitHub is a service where software projects track issues and changes.

In plain words
What is it for?
Use it after drafting a report to choose direct filing with gh or a paste-ready handoff, request approval, and complete the report safely.
Why use it?
It makes the approval boundary explicit and checks whether the GitHub command-line tool can file the issue before asking for consent. It also protects tokens and other credentials.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after drafting a report to choose direct filing with gh or a paste-ready handoff, request approval, and complete the report safely.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lingtai-ai/lingtai/filing-flow
Install

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.

Any agent
npx skills add Lingtai-AI/lingtai --skill filing-flow
Clone the repo
git clone --depth 1 https://github.com/Lingtai-AI/lingtai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for issue-report-filing-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/lingtai-ai/lingtai/filing-flow/github.svg)](https://agentmods.dev/skills/lingtai-ai/lingtai/filing-flow)
Your own site
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/filing-flow"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/filing-flow/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.

agentmods 80×15 button for issue-report-filing-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/filing-flow"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/filing-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 30
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01761
Opus 5 $0.00036 $0.00881
Sonnet 5 $0.00014 $0.00352
Haiku 4.5 $0.00007 $0.00176

Measured 9d ago against content hash 3ebabc140816, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

issue-report-filing-flow 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 9d 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.

tui/internal/preset/skills/lingtai-issue-report/reference/filing-flow/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue report — filing flow

This is a nested lingtai-issue-report reference. It governs everything after the report is drafted: human consent, detecting whether gh can file directly, the two filing paths, and proactive surfacing.

The boundary — permission required, always

You never open a GitHub issue without an explicit "yes" from the human. The human is the accountable owner of what gets filed under their name. Even if gh is authenticated and you have a shell, the per-issue consent is non-negotiable. Your role is to:

  1. Assemble a structured report (see the report-template reference)
  2. Send the report through the appropriate channel to your parent avatar (if you're an avatar) AND to the human
  3. Check whether gh is available and authenticated (see "Filing path" below)
  4. Ask the human's permission, naming the path you'd take (direct gh filing vs. paste-into-browser)
  5. Only then act — file it via gh if they say yes, or hand them the title/body if they prefer to file manually

If the human declines, drop it. Don't nag, don't auto-retry on the next turn. Their call.

Filing path — detect gh first

Before you ask the human for permission, run a quick read-only probe to see whether the GitHub CLI is installed AND there's a way to authenticate. There are two acceptable auth sources — either is enough to make Path A available:

  1. Existing gh auth — the host already has a logged-in account.
  2. A GH_TOKEN the human provided this session — they pasted a personal access token into chat (or it's already in your shell env). gh reads GH_TOKEN from the environment per-invocation, so no gh auth login is needed.

Probe:

# Is gh installed?
command -v gh

# Is gh already authenticated?
gh auth status 2>&1

Interpret: gh installed and either auth source present → Path A is available. gh missing, or neither source present → Path A is out; fall through to Path B.

Do not run gh issue create during the probe. Do not echo, log, or commit the token. The probe is read-only; the actual filing happens only after the human says yes.

Read the full file on GitHub · 111 lines

Changes

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.

  1. 9d ago First seen · 111 lines · 71 tokens per session scan A 3ebabc140816

Subscribe to this mod's changes

issue-report-filing-flow is a skill published in the GitHub repository Lingtai-AI/lingtai (700 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 1,761 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 2026-08-30.