counterpoise-ledger: Skill for Claude Code

.claude/skills/fix-reported-issue/SKILL.md

fix-reported-issue is a skill for Claude Code from jeffjjohnston/counterpoise-ledger. It costs 86 tokens per session (1,271 once invoked), scanned A, original, MIT.

A workflow for finding and fixing the oldest unresolved report from a production issue table. Production means the live version of an application used by real users.

In plain words
What is it for?
Use it to triage reported bugs, quote the original report, make and verify the fix, track related work when the project uses beads, commit the change, and mark the report resolved.
Why use it?
It gives user-reported bugs a defined path from investigation through testing, resolution, and tracking.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is jeffjjohnston/counterpoise-ledger's own configuration. It tells Claude Code how to work on counterpoise-ledger 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 counterpoise-ledger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jeffjjohnston/counterpoise-ledger. 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/jeffjjohnston/counterpoise-ledger/main/.claude/skills/fix-reported-issue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jeffjjohnston/counterpoise-ledger

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 fix-reported-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffjjohnston/counterpoise-ledger/fix-reported-issue/github.svg)](https://agentmods.dev/skills/jeffjjohnston/counterpoise-ledger/fix-reported-issue)
Your own site
<a href="https://agentmods.dev/skills/jeffjjohnston/counterpoise-ledger/fix-reported-issue"><img src="https://agentmods.dev/badge/skills/jeffjjohnston/counterpoise-ledger/fix-reported-issue/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 fix-reported-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffjjohnston/counterpoise-ledger/fix-reported-issue"><img src="https://agentmods.dev/badge/skills/jeffjjohnston/counterpoise-ledger/fix-reported-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,271 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.
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 $0.00086 $0.01271
Opus 5 $0.00043 $0.00635
Sonnet 5 $0.00017 $0.00254
Haiku 4.5 $0.00009 $0.00127

Measured 9d ago against content hash 3e0bc7c78cf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fix-reported-issue 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/fix-reported-issue/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintainer setup — adapt paths for your fork. Container names are pinned by name: in docker-compose.yml, so those are the same in every checkout.

Fix Reported Issue

This skill handles the full lifecycle of a user-reported issue: find it, fix it, verify the fix, commit, and mark it resolved. The issue_reports table lives in the production PostgreSQL database and is populated by in-app user feedback.

Work tracking

This project may use beads (bd) for issue tracking. Test for it once, before step 1:

command -v bd >/dev/null 2>&1 && bd ready

If bd answers, track the work in it:

When Do
After step 3, before you edit anything bd create --title="<short summary>" --type=bug --priority=2 --description="issue_reports #<id>, reported on <page>: <the user's own words>", then bd update <bead-id> --claim
Any time you find work you are not doing now bd create it, with enough detail that nobody re-derives the investigation
With step 7 bd close <bead-id> --reason="<what changed>", then bd dolt push

Three things about that table are load-bearing:

  • Quote the report in the description. A future reader has no access to the production database, so a bead that says "fix the sync page" is a dead end. Paste what the user wrote.
  • bd dolt push is what makes the close durable. Issue data lives in a local database; without the push it exists on one machine.
  • Filing discovered work is the point. A reported issue routinely exposes an adjacent bug, a missing test, or a refactor. Step 4 tells you to keep the change minimal, and that instruction only holds if the work you are declining has somewhere to go. Widening the fix, or dropping the finding silently, are both failures of this step.

If bd does not answer, skip this section and change nothing else in the workflow. The issue_reports row is already the record of the fix; beads adds a home for the discovered work, which that row has no field for.

Read the full file on GitHub · 117 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 · 117 lines · 86 tokens per session scan A 3e0bc7c78cf8

Subscribe to this mod's changes

fix-reported-issue is a skill published in the GitHub repository jeffjjohnston/counterpoise-ledger (6 stars, last pushed 12d ago), licensed MIT. It adds 86 tokens to every session and 1,271 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.

Related

Other skills, from other repositories

a11y-debugging

Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.

ChromeDevTools/chrome-devtools-mcp · 50 tokens

chrome-devtools

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).

ChromeDevTools/chrome-devtools-mcp · 55 tokens

n8n-error-handling

Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…

czlonkowski/n8n-mcp · 128 tokens

agentcore-investigation

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.

awslabs/mcp · 52 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

memory-leak-debugging

Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to capture, compare, or inspect heap snapshots with Chrome DevTools MCP memory tools.

ChromeDevTools/chrome-devtools-mcp · 52 tokens