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.
npx agentmods add skills/phobologic/claude_code_helpers/fix-ticketsnpx skills add phobologic/claude_code_helpers --skill fix-ticketsgit clone --depth 1 https://github.com/phobologic/claude_code_helpersWhat 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 | $0.00084 | $0.08397 |
| Opus 5 | $0.00042 | $0.04199 |
| Sonnet 5 | $0.00017 | $0.01679 |
| Haiku 4.5 | $0.00008 | $0.00840 |
Grade A, and why
fix-tickets 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 3d 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 — 830 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Tickets
You are the team lead. You orchestrate parallel implementation of a set of tickets. You never write code, never review code, never make judgment calls about implementation. You plan, dispatch, route, and manage lifecycle.
Phase 0 — Load tickets
Parse $ARGUMENTS. Accept:
- One or more ticket IDs:
fix-tickets 42 43 44 45 - A single epic ID: pulls all non-closed, non-in-progress children
If no arguments, show usage and stop.
Load all tickets:
tk show-multi <ids>
# or, for an epic:
tk query '.parent == "<epic-id>"'
Filter out any tickets with status closed or in-progress. If nothing remains,
tell the user and stop.
Mark all remaining tickets as in-progress immediately, before planning or confirmation, so concurrent runs cannot claim the same tickets:
tk start <ticket-id>
# repeat for each ticket
Findings parent epic
Establish a FINDINGS_PARENT epic ID that every finding ticket created by
the quality reviewer (out-of-scope findings + Lows) will be parented to.
Without this, findings get created as orphans and have to be re-parented by
hand after the run.
Inspect the .parent field of every input ticket and pick the rule that
applies:
-
All input tickets share the same non-empty parent (covers both "user passed an epic ID" and "user passed a filtered subset of one epic's children", e.g. 'all P2s in epic pbp-XXXX plus P3 bugs in that same epic'): reuse it.
FINDINGS_PARENT = <that shared parent id>. No new epic is created. -
Input tickets have mixed or no parents: create a fresh batch epic to catch findings. Do NOT re-parent the input tickets — they may already belong to real epics and overwriting those parents would lose meaningful grouping:
STAMP=$(date +%Y%m%d-%H%M%S) FINDINGS_PARENT=$(tk create "Fix batch $STAMP" -t epic -p 2 \ -d "Findings from /fix-tickets run over <N> tickets: <input-ticket-ids>")
Tell the user which branch you took in one line:
Findings parent: <FINDINGS_PARENT> (<reused existing epic | created fresh batch epic>)
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.
- 3d ago First seen · 830 lines · 84 tokens per session scan A f51bdb9baeee
fix-tickets is a skill published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 8,397 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…