Borrowing it
Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/skills/start-issue/SKILL.mdgit clone --depth 1 https://github.com/auerbachb/claude-code-configWrote 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.
[](https://agentmods.dev/skills/auerbachb/claude-code-config/start-issue)<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/start-issue"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/start-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.
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/start-issue"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/start-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 43 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Data Exfiltration · line 270 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high Privilege Escalation · line 321 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 322 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 396 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.09788 |
| Opus 5.5 | $0.00024 | $0.03915 |
| Sonnet 5.5 | $0.00012 | $0.01958 |
| Haiku 4.5 | $0.00006 | $0.00979 |
Grade A, and why
start-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automate the full issue-to-coding flow: create issue (if needed) → wait for CR plan → merge plans → create worktree + branch → output ready-to-code summary. Replaces 5-10 minutes of manual setup per issue.
Step 0: Resolve shared tooling
/start-issue is symlinked into every repo, but its helper scripts and reference docs are not — most repos carry no .claude/ directory. Resolve them; never invoke a bare .claude/scripts/… path. Full contract and the classified dependency inventory: .claude/reference/portable-skill-resolution.md (issue #1189).
resolve_script() {
local name="$1" candidate
for candidate in \
"$HOME/.claude/skills-worktree/.claude/scripts/$name" \
"$HOME/.claude/scripts/$name" \
".claude/scripts/$name"; do
if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
done
return 1
}
ISSUE_CLAIM=$(resolve_script issue-claim.sh || true)
CR_PLAN=$(resolve_script cr-plan.sh || true)
ISSUE_DEDUP=$(resolve_script issue-dedup.sh || true)
REPO_ROOT_SH=$(resolve_script repo-root.sh || true)
SPLIT_THRESHOLDS=$(resolve_script split-thresholds.sh || true)
Read reference docs through the same order — $HOME/.claude/skills-worktree/.claude/reference/<name> first, then $HOME/.claude/reference/, then .claude/reference/. That covers chip-launching.md, autofile-dedup.md, and issue-claim.md.
When something does not resolve, say so in one line; never skip the contract silently.
-
chip-launching.mdunreadable → required. PrintERROR: chip-launching.md not found (checked all three paths) — PM-context inline gate unavailableand stop before offering a chip; without the gate a subagent-fit issue routes to its own thread instead of the inline pipeline (#1189). -
ISSUE_CLAIMempty → optional, but loud. PrintDEGRADED: issue-claim.sh not found (checked all three paths) — Step 2b gate cannot run, proceeding unclaimedand continue. Say it once, in the visible output — an unclaimed start that nobody was told about is how two threads end up on one issue. -
CR_PLANempty → optional. PrintDEGRADED: cr-plan.sh not found (checked all three paths) — CR plan detection skippedand go straight to Step 4; Claude's own plan and the issue-body merge are still mandatory. -
ISSUE_DEDUPempty → optional. PrintDEGRADED: issue-dedup.sh not found (checked all three paths) — duplicate search skippedand continue. -
REPO_ROOT_SHempty → optional. Fall back togit worktree list --porcelain | awk '/^worktree /{sub(/^worktree /, ""); print; exit}'; no warning needed, the inline form is equivalent. -
SPLIT_THRESHOLDSempty → optional. PrintDEGRADED: split-thresholds.sh not found (checked all three paths) — using default thresholds 180/120and read Step 7's time trigger against those defaults. The thresholds are knobs, so an unresolved helper must be said, not silently defaulted — a loweredSPLIT_OVER_MINthat never loaded is a split that never fires.Read both knobs, in one call, the way
/issue-maker's sizing block does —"$SPLIT_THRESHOLDS" --json, thenSPLIT_OVER_MINandINCREMENT_BOUND_MINout of it withjq, both or neither, keeping the documented180/120on a partial read. Step 7's trigger only needs the first, but its split branch runs/subagentStep 5.1, which bounds every child it files at or under the second; resolving one knob here and letting the decomposition fall back to a default the config overrode is how a chain gets filed against a bound nobody chose.
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.
- 1mo ago Changed · +20 lines 24448e0745e9
- 1mo ago Changed 5485fce0396c
- 2mo ago First seen · 415 lines · 61 tokens per session scan A 35bacf9b1dee
start-issue is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 9,788 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.
robin
Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…
jira
Unified Jira entry point. Routes to preview (default), create, or review subcommands.
standup
Generate standup summary from git history, track progress, and Jira/GitHub activity. Read-only — makes no changes to the codebase.
status
Display current progress of Draft tracks and active tasks. Shows phases, completion percentages, and blocked items.
github-brief-intake
Use when GitHub work should enter the repository work-intake route, including an Issue, Milestone, view, or cross-repository selection.