discover-work

discover-work is a skill for Claude Code, Codex from Destrayon/Connapse. It costs 77 tokens per session (1,771 once invoked), scanned A, original, MIT.

A research process for finding unrecorded tasks, code gaps, technical debt, and improvement ideas across a project. Technical debt means existing shortcuts or weaknesses that may make future work harder.

In plain words
What is it for?
Use it for backlog discovery, codebase audits, technical-debt reviews, and finding work that has not yet been filed as a task.
Why use it?
It looks beyond the current issue list by examining code markers, GitHub activity, project boards, and architecture documents.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/destrayon/connapse/discover-work
Any agent
npx skills add Destrayon/Connapse --skill discover-work
Clone the repo
git clone --depth 1 https://github.com/Destrayon/Connapse

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 discover-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/destrayon/connapse/discover-work.svg)](https://agentmods.dev/skills/destrayon/connapse/discover-work)
Your own site
<a href="https://agentmods.dev/skills/destrayon/connapse/discover-work"><img src="https://agentmods.dev/badge/skills/destrayon/connapse/discover-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.01771
Opus 5 $0.00039 $0.00886
Sonnet 5 $0.00015 $0.00354
Haiku 4.5 $0.00008 $0.00177

Measured 5d ago against content hash 2513ca8a7ca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

discover-work 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 5d 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/discover-work/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discover Work

Perform thorough research across all project surfaces to discover new tasks, gaps, technical debt, and improvement ideas that haven't been captured yet.

Overview

This skill systematically investigates six research dimensions, synthesizes findings, and presents a prioritized list of discovered work items. It goes beyond what /next-task does (which picks from existing issues) — this skill finds new work that nobody has filed yet.

Research Dimensions

Work through each dimension. Use the Agent tool to parallelize independent research. Present findings grouped by dimension, then synthesize into a final prioritized list.

1. Codebase Markers

Search the entire src/ tree for signals of incomplete or problematic code:

Patterns to search (case-insensitive):
  TODO, FIXME, HACK, WORKAROUND, TEMPORARY, DEFER, XXX, BUG, PERF,
  NotImplementedException, throw new NotSupportedException,
  "// removed", "// disabled", "// old", "// legacy"

For each hit, read surrounding context (5-10 lines) to understand whether it's:

  • A genuine gap that needs a ticket
  • A known deferral already tracked in .claude/state/issues.md
  • A false positive (e.g., test code, intentional placeholder)

Skip false positives. Flag genuine gaps.

2. GitHub Issues & Discussions

Use gh CLI to pull:

# Open issues with details
gh issue list --state open --limit 100 --json number,title,labels,milestone,body,assignees,createdAt,updatedAt

# Closed issues (look for reopened patterns, incomplete fixes)
gh issue list --state closed --limit 30 --json number,title,labels,closedAt,body

# Discussions
gh api repos/{owner}/{repo}/discussions --jq '.[] | {number, title, category: .category.name, body, comments: .comments, created_at}'

# PRs (open and recently merged — look for follow-up items)
gh pr list --state merged --limit 20 --json number,title,body,mergedAt,labels
gh pr list --state open --limit 10 --json number,title,body,labels

Look for:

  • Issues that are stale (no updates in 2+ weeks, no assignee, needs-triage label)
  • Issues missing labels, milestones, or size estimates
  • Closed issues whose fixes were partial (check for "deferred", "follow-up", "TODO" in close comments)
  • Discussions with unresolved questions or design decisions
  • Merged PRs that mention "follow-up" or "deferred" work
  • Open PRs that have been sitting without review

Read the full file on GitHub · 196 lines

Files

What ships with it

1 file 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.

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. 5d ago First seen · 196 lines · 77 tokens per session scan A 2513ca8a7ca9

Subscribe to this mod's changes

discover-work is a skill published in the GitHub repository Destrayon/Connapse (16 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,771 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.

Related

Other skills, from other repositories

blazorbindings-maui-third-party

Integrate third-party .NET MAUI control libraries into BlazorBindings.Maui apps by generating Razor wrappers, registering attached properties, and bridging to native elements for imperative APIs such as popups or bottom sheets. Use when adding, updating, or troubleshooting a MAUI control package in a…

Dreamescaper/BlazorBindings.Maui · 85 tokens

embeddings-search

Use when choosing an embedding model, chunk size, or query form, when semantic search returns irrelevant results, when adding hybrid BM25+vector or a reranker, or when a retrieval change needs a number (recall@k, nDCG, MRR). NOT operating the store — index tuning, quantization (that is vector-db) — nor the…

ericrisco/rsc-harness · 88 tokens

mapsui

Use when embedding interactive 2D maps in .NET desktop (WinForms/WPF) or mobile (MAUI) applications — tile layers, vector features, map controls. Mapsui: cross-platform .NET map component library.

znlgis/opengis-skills · 49 tokens

cocosearch-review-pr

Use when reviewing a GitHub PR or GitLab MR by URL. Fetches diff and metadata via API, then uses CocoSearch for blast radius analysis, dependency impact, pattern consistency, and test coverage assessment. Read-only by default; optionally pushes findings back as inline PR/MR comments after your confirmation.

VioletCranberry/coco-search · 68 tokens

cocosearch-add-language

Use when adding support for a new programming language or config format to CocoSearch. Guides through all paths (handler, symbol extraction, context expansion) with registration checklists. For grammar handlers, use cocosearch-add-grammar.

VioletCranberry/coco-search · 53 tokens

cocosearch-add-extractor

Use when adding a dependency extractor for a language or grammar. Guides through pre-checks, extractor implementation, optional module resolver, tests, and registration. Enables deps tree, deps impact, and dependency-enriched search for the target language.

VioletCranberry/coco-search · 57 tokens