aidoc-flow-framework: Skill for Claude Code

.agents/skills/aidoc-triage/SKILL.md

aidoc-triage is a skill for Claude Code, Codex from vladm3105/aidoc-flow-framework. It costs 65 tokens per session (3,144 once invoked), scanned A, original, MIT.

A workflow for checking GitHub issues, which are tracked reports of problems or requested changes in a code project. It verifies their claims, judges priority, applies labels, and adds a triage note without implementing or closing the issue.

In plain words
What is it for?
Use it to review, scope, and label issues before work begins, using the current issue state, comments, and repository files as evidence.
Why use it?
It reduces the risk of starting work from outdated line numbers, unsupported claims, or the wrong priority. It also keeps issue assessment separate from making code changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is vladm3105/aidoc-flow-framework's own configuration. It tells Claude Code and Codex how to work on aidoc-flow-framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aidoc-flow-framework configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/ya/devd/technology_stack.

Reuse

Borrowing it

Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vladm3105/aidoc-flow-framework/dev/.agents/skills/aidoc-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

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 aidoc-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/aidoc-triage/github.svg)](https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/aidoc-triage)
Your own site
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/aidoc-triage"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/aidoc-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.

agentmods 80×15 button for aidoc-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/aidoc-triage"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/aidoc-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00065 $0.03144
Opus 5.5 $0.00026 $0.01258
Sonnet 5.5 $0.00013 $0.00629
Haiku 4.5 $0.00006 $0.00314

Measured 10d ago against content hash 9580f84f92a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aidoc-triage scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Flaky pool**: `curl: (6) Could not resolve host: github.com` on trivy/dep-scan = DNS flake — `gh run rerun <run-id> --failed`, don't chase.
.agents/skills/aidoc-triage/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aidoc-flow-framework Issue Triage

Framework-local instance of the triage workflow (repo-specific taxonomy, defect classes, and standing rules inline). The generic parameterized issue-triage is tracked for canon curation in aidoc-flow-claude-agents-config#114; this file stays in use regardless of that outcome.

Triage = assess + label + comment. Triage NEVER implements, closes, or rewrites history.

0. Preconditions

  • gh authenticated (gh auth status). Work from the framework checkout, on dev, clean tree.
  • Project memory holds standing rules and the session handoff — read them first (the repo AGENTS.md chain plus the memory store); they override anything stale below. If absent (fresh machine), proceed without it.

1. Fetch the issue live

gh issue view <N> --repo vladm3105/aidoc-flow-framework \
  --json state,title,labels,body,comments

Record: state, current labels, existing comments, every factual claim (file paths, line numbers, counts, error text). Filed line numbers rot fast — treat them as hints, never facts.

If the issue is already CLOSED, stop and report that with evidence — never triage a corpse, never re-triage into a closed thread.

Review the full comment thread

The body is only the opening claim — read every comment, oldest first:

  • Attribute each follow-up claim (correction, reproduction, "+1", proposed fix) to its author and date; verify load-bearing ones under §2 exactly like body claims.
  • Corrections inside the thread supersede the body — triage the corrected claim, and name what it supersedes in the note.
  • A prior triage note changes the job: post a delta per §4, never a duplicate full note. If an earlier verdict's evidence rotted (file moved, rule renumbered, VERSION advanced), say so with the fresh check.
  • Stale or resolved sub-threads get one line in the note ("comment dated YYYY-MM-DD no longer reproduces — "), never an in-thread argument with the commenter.

2. Verify each claim against the tree (the core discipline)

Read the full file on GitHub · 163 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. 10d ago Changed · +3 lines 9580f84f92a4
  2. 29d ago Changed · +45 lines a282dc049c0d
  3. 1mo ago Changed · +23 lines d85fbe12bf9e
  4. 1mo ago First seen · 92 lines · 65 tokens per session scan A dc8e2fb510f1

Subscribe to this mod's changes

aidoc-triage is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 3,144 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.

Related

Other skills, from other repositories

bug-triage

Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.

Donchitos/Claude-Code-Game-Studios · 30 tokens

triage-issue-reports

Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.

backnotprop/pstack · 46 tokens

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

triage-issue

Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…

atlassian/atlassian-mcp-server · 116 tokens

moai-lane-watchdog

One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…

modu-ai/moai-adk · 86 tokens

investigation

Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).

me2resh/apexyard · 26 tokens