tokentelemetry: Skill for Claude Code

.claude/skills/issue-brief/SKILL.md

issue-brief is a skill for Claude Code from VasiHemanth/tokentelemetry. It costs 195 tokens per session (1,508 once invoked), scanned A, original, MIT.

A guide for explaining a GitHub issue, discussion, or feature request before development begins. GitHub issues and discussions are places where people report problems, ask questions, or propose changes.

In plain words
What is it for?
Use it to summarise a GitHub report, trace a failure through real endpoints, connect the behaviour to specific files and lines, and estimate the implementation work.
Why use it?
It turns a report into a clear description of the request, the current code behaviour, and the work involved. This helps determine whether the problem is already solved and what implementation would require.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is VasiHemanth/tokentelemetry's own configuration. It tells Claude Code how to work on tokentelemetry 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 tokentelemetry configures →

Reuse

Borrowing it

Nothing to install: this file belongs to VasiHemanth/tokentelemetry. 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/VasiHemanth/tokentelemetry/main/.claude/skills/issue-brief/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/VasiHemanth/tokentelemetry

Made for: Claude Code.

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-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/vasihemanth/tokentelemetry/issue-brief/github.svg)](https://agentmods.dev/skills/vasihemanth/tokentelemetry/issue-brief)
Your own site
<a href="https://agentmods.dev/skills/vasihemanth/tokentelemetry/issue-brief"><img src="https://agentmods.dev/badge/skills/vasihemanth/tokentelemetry/issue-brief/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-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/vasihemanth/tokentelemetry/issue-brief"><img src="https://agentmods.dev/badge/skills/vasihemanth/tokentelemetry/issue-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,508 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 pass 7 Sept 2026
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 $0.00195 $0.01508
Opus 5 $0.00097 $0.00754
Sonnet 5 $0.00039 $0.00302
Haiku 4.5 $0.00019 $0.00151

Measured 9d ago against content hash a9b0be692c3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

issue-brief 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.

.claude/skills/issue-brief/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

issue-brief — explain an issue before building it

The output is an explanation, not a design doc and not a diff. Assume the reader has not read the reporter's post and does not have the file layout in their head. Lead with the plain meaning; the architecture comes fourth.

1. Fetch the thing

Issues:

gh issue view <number-or-url> --json number,title,state,author,createdAt,closedAt,labels,body,comments

Discussions need GraphQL. There is no gh discussion command (verified on gh 2.92), and gh issue view will not resolve a discussion number. Use:

gh api graphql -f query='
{ repository(owner:"VasiHemanth", name:"tokentelemetry") {
    discussion(number: NNN) {
      number title url category{name} author{login} createdAt body
      comments(first:20){ nodes { author{login} body } }
    } } }'

Then, before writing anything:

  • Check it isn't already done. Grep the codebase for the feature's nouns. Issue 135 (Pi agent support) was closed and fully shipped; the tell was PI_SESSIONS_DIR and test_pi_scan.py already sitting on main.
  • Search for the same root cause elsewhere, open and closed (gh issue list --search). Issues 198 and 96 were the same two-port problem reported twice, a year apart, by different people.
  • Check open PRs that touch the files you'd touch (gh pr list). They set the landing order.

2. Answer in this order

  1. What the reporter actually wants, in one or two sentences of plain language, jargon stripped. Name them. Link the earlier issue or PR if it's a repeat.
  2. A concrete walkthrough of the problem. Pick one realistic setup and trace it as numbered steps, with real hostnames, real ports, real endpoints. Never "suppose a user does X". Say what the user sees first, then why it happens.
  3. How it works today, only the part that bears on the issue, with file.py:line anchors so the claim can be checked.
  4. What implementing it would take: the shape of the change and which layer it belongs in, not a full diff.
  5. Traps and interactions. Security regressions, open PRs on the same files, closed issues with the same root cause, what has to land first.
  6. A verdict and one next step ("worth accepting, want me to draft the reply comment?").

Read the full file on GitHub · 121 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 · 121 lines · 195 tokens per session scan A a9b0be692c3c

Subscribe to this mod's changes

issue-brief is a skill published in the GitHub repository VasiHemanth/tokentelemetry (344 stars, last pushed yesterday), licensed MIT. It adds 195 tokens to every session and 1,508 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

prd-review-framework

Use when reviewing a PRD for goal clarity, scope, assumptions, and implementation readiness.

staruhub/CrewClaw · 22 tokens

gini-bug-report

File a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill.

Open-Curiosity/gini-agent · 47 tokens

design-inventory

Use to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token…

closedloop-ai/claude-plugins · 173 tokens

prd-creator

This skill helps PMs draft lightweight PRDs. It should be used when a PM wants to define a new feature, brainstorm requirements, or prep for sprint planning. Triggers include "I have a feature idea", "help me write a PRD", "let's break this into stories", or "what do I need for sprint planning". Optimized for speed …

closedloop-ai/claude-plugins · 89 tokens

upload-artifact

Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload…

closedloop-ai/claude-plugins · 103 tokens

cross-repo-cache

Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…

closedloop-ai/claude-plugins · 81 tokens