mine-tasks
Point at any repo (GitHub, GitLab, Bitbucket, Azure DevOps, self-hosted, or local) and get eval tasks that compare baseline coding agents vs MCP-augmented…
Skill by sourcegraph
Chalk Labs
Need help deploying mine-tasks?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sourcegraph-mine-tasks
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, cloud, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mine-tasks
What's inside
- Skill name
mine-tasks- Description
- Point at any repo (GitHub, GitLab, Bitbucket, Azure DevOps, self-hosted, or local) and get eval tasks that compare baseline coding agents vs MCP-augmented agents. Mines merged PRs/MRs for real code-change tasks, auto-generates ground truth from patches, produces runnable Docker environments for both configs. Works with private repos on any host. Triggers on mine tasks, propose tasks, discover tasks, find tasks, analyze repo for tasks, eval my repo, benchmark my repo.
- License
- Apache-2.0
- Instructions
- 1,088 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- body: 1088 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# Mine Tasks
Point at a codebase — on any code host or locally — and get a baseline-vs-MCP comparison for AI coding agents. Mines real merged PRs/MRs to create eval tasks where agents must reproduce known fixes/features, then measures whether MCP tools (code search, semantic indexing) help agents find the right code faster.
Works with GitHub, GitLab, Bitbucket, Azure DevOps, self-hosted Gitea/Forgejo, or plain local git repos.
**Two workflows:**
- **Quick eval** (default): Mine 5-10 SDLC tasks from merged PRs/MRs, auto-generate ground truth, produce runnable Dockerfiles, print `docker run` commands. ~10 minutes to a working eval.
- **Full mining**: Deep analysis for contributing tasks to CodeScaleBench. Includes org-scale tasks, scoring, reviewer extraction, and `/scaffold-task` integration.
---
## Host Adapter Reference
All host-specific operations go through a detected adapter. The skill auto-detects the host from the URL and uses the appropriate CLI/API. When no API is available, it falls back to git-only mode.
### Host Detection
| URL Pattern | Host | CLI | Adapter |
|-------------|------|-----|---------|
| `github.com/*` | GitHub | `gh` | `github` |
| `gitlab.com/*` or self-hosted with `/api/v4/` | GitLab | `glab` | `gitlab` |
| `bitbucket.org/*` | Bitbucket | `curl` (REST v2) | `bitbucket` |
| `dev.azure.com/*` or `*.visualstudio.com/*` | Azure DevOps | `az repos` | `azure` |
| `*.gitea.*` or `*.forgejo.*` or user-specified | Gitea/Forgejo | `curl` (REST) | `gitea` |
| Local path (no remote) | — | — | `git_only` |
| Any other remote | — | — | `git_only` |
### Merge Request Operations
The skill needs these operations from each host. "MR" is used generically below (= PR on GitHub/Bitbucket, MR on GitLab, PR on Azure DevOps).
#### List merged MRs
```bash
# GitHub
gh pr list --repo {REPO} --state merged --limit {LIMIT} \
--json number,title,body,labels,files,additions,deletions,closedAt,mergedAt
# GitLab
glab mr list --repo {REPO} --state merged --per-page {LIMIT} \
--output json
# Bitbucket
curl -s -u "${BB_USER}:${BB_APP_PASSWORD}" \
"https://api.bitbucket.org/2.0/repositories/{REPO}/pullrequests?state=MERGED&pagelen={LIMIT}"
# Azure DevOps
az repos pr list --organization {ORG_URL} --project {PROJECT} \
--repository {REPO_NAME} --status completed --top {LIMIT} --output json
# Gitea / Forgejo
curl -s -H "Authorization: token ${GITEA_TOKEN}" \
"{GITEA_URL}/api/v1/repos/{OWNER}/{REPO}/pulls?state=closed&sort=updated&limit={LIMIT}"
# git-only fallback (no API)
git log --merges --oneline --since="6 months ago" -n {LIMIT}
# Or for repos that use squash merges:
git log --oneline --since="6 months ago" --grep="fix\|feat\|bug\|refactor" -n {LIMIT}
```
#### Get MR diff
```bash
# GitHub
gh pr diff {NUMBER} --repo {REPO}
# GitLab
glab mr diff {NUMBER} --repo {REPO}
# Bitbucket
curl -s -u "${BB_USER}:${BB_APP_PASSWORD}" \
"https://api.bitbucket.org/2.0/repositories/{REPO}/pullrequests/{NUMBER}/diff"
# Azure DevOps
az repos pr diff --id {NUMBER} --organization {ORG_URL} --output json
# Or: query the commits and diff them
az repos pr list --id {NUMBER} --query "[].{source: sourceRefName, target: targetRefName}" --output json
# Gitea / Forgejo
curl -s -H "Authorization: token ${GITEA_TOKEN}" \
"{GITEA_URL}/api/v1/repos/{OWNER}/{REPO}/pulls/{NUMBER}.diff"
# git-only fallback
git diff {BASE_COMMIT}..{MERGE_COMMIT}
```
#### Get MR metadata (base commit, merge commit, author, linked issue)
```bash
# GitHub
gh pr view {NUMBER} --repo {REPO} --json mergeCommit,baseRefOid,author,title,body,labels
# GitLab
glab mr view {NUMBER} --repo {REPO} --output json
# Linked issues: parsed from MR description ("Closes #123") or via API
glab api "projects/{PROJECT_ID}/merge_requests/{NUMBER}/closes_issues"
# Bitbucket
curl -s -u "${BB_USER}:${BB_APP_PASSWORD}" \
"https://api.bitbucket.org/2.0/repositories/{REPO}/pullrequests/{NUMBER}"
# Azure DevOps
az repos pr show --id {NUMBER} --organization {ORG_URL} --output json
# Linked work items:
az repos pr work-item list --id {NUMBER} --organization {ORG_URL} --output json
# Gitea / Forgejo
curl -s -H "Authorization: token ${GITEA_TOKEN}" \
"{GITEA_URL}/api/v1/repos/{OWNER}/{REPO}/pulls/{NUMBER}"
# git-only fallback
# Parse from merge commit message: "Merge pull request #N" or "Fixes #N"
git log --format="%H %s" --merges -n 50 | grep -i "fix\|feat\|bug\|refactor"
# Base commit = first parent of merge commit
git rev-parse {MERGE_COMMIT}^1
```From sourcegraph/CodeScaleBench, Apache-2.0.
More from sourcegraph/CodeScaleBench
- 0.499score
triage-failure
sourcegraph
Investigate a specific failed benchmark task — read logs, identify root cause, check if known pattern, suggest fix.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
check-infra
sourcegraph
Verify infrastructure readiness before launching benchmark runs — tokens, Docker, disk, credentials.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
archive-run
sourcegraph
Archive old completed benchmark runs to save disk space and speed up scans.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
sync-metadata
sourcegraph
Reconcile task metadata between selected_benchmark_tasks.json and task.toml files.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
validate-tasks
sourcegraph
Pre-flight validation of benchmark tasks before launching runs.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
whats-next
sourcegraph
Analyze current benchmark state and recommend what to work on next.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
compare-configs
sourcegraph
Compare benchmark results across agent configurations (baseline, SG_full).
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
quick-rerun
sourcegraph
Run a single benchmark task locally to verify a fix.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
cost-report
sourcegraph
Token and cost analysis per run, suite, and config.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
run-status
sourcegraph
Quick status check on the currently active benchmark run.
SkillDFreshness: D★ 37Claude Code +9 - 0.495score
ir-analysis
sourcegraph
Compute information retrieval quality metrics (precision, recall, MRR, nDCG, MAP) comparing file retrieval across baseline and MCP configs against ground truth.
SkillDFreshness: D★ 37Claude Code +9 - 0.495score
generate-report
sourcegraph
Generate the aggregate CSB evaluation report from completed Harbor runs.
SkillDFreshness: D★ 37Claude Code +9
Signals
- Stars
- 37
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- Mar 17, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/sourcegraph/CodeScaleBench
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sourcegraph
- 0.499score
archive-run
sourcegraph
Archive old completed benchmark runs to save disk space and speed up scans.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
quick-rerun
sourcegraph
Run a single benchmark task locally to verify a fix.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
check-infra
sourcegraph
Verify infrastructure readiness before launching benchmark runs — tokens, Docker, disk, credentials.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
compare-configs
sourcegraph
Compare benchmark results across agent configurations (baseline, SG_full).
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
cost-report
sourcegraph
Token and cost analysis per run, suite, and config.
SkillDFreshness: D★ 37Claude Code +9 - 0.499score
run-status
sourcegraph
Quick status check on the currently active benchmark run.
SkillDFreshness: D★ 37Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get mine-tasks running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
mine-tasks skill. Agent Mart. https://agentmart.dev/skills/sourcegraph-mine-tasks (last updated 2026-10-24)