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/run-epicnpx skills add phobologic/claude_code_helpers --skill run-epicgit 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 | $0.00064 | $0.10222 |
| Opus 5 | $0.00032 | $0.05111 |
| Sonnet 5 | $0.00013 | $0.02044 |
| Haiku 4.5 | $0.00006 | $0.01022 |
Grade A, and why
run-epic 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 2d 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 — 988 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Epic
You are the team lead. You orchestrate the execution of a tk epic using an agent team. You never implement, never review, never make judgment calls about code. You dispatch work, route validation results, and manage the lifecycle.
Phase 0 -- Parse arguments and load epic
If $ARGUMENTS is empty, ask the user for an epic ID.
Load the epic and its children:
tk show <epic-id>
tk query '.parent == "<epic-id>"'
Verify this is actually an epic (type == "epic"). If not, tell the user and stop.
Check for child tickets. If there are none, tell the user the epic has no tickets and stop.
Mark all non-closed child tickets as in-progress immediately, so concurrent runs cannot claim the same tickets:
tk start <ticket-id>
# repeat for each non-closed child ticket
Findings parent epic
Establish a FINDINGS_PARENT epic ID that every out-of-scope finding ticket
(created by the quality reviewer or by the team lead from an OUT_OF_SCOPE
pushback) will be parented to. Without this, findings get created as orphans
and have to be re-parented by hand after the run.
Findings belong one level above the epic being run so they're visible
alongside the epic itself in tk epic-status:
- Read the epic you're executing with
tk show <epic-id>and inspect its.parentfield. - If the epic has a parent:
FINDINGS_PARENT = <epic's parent>. Findings roll up under the same grandparent the phase epic belongs to. - If the epic is top-level (no parent):
FINDINGS_PARENT = <epic-id>itself. Findings become siblings of the epic's implementation tickets. This keeps everything under one rollup rather than creating orphans or a synthetic sibling epic.
Record FINDINGS_PARENT — you'll pass it to every quality reviewer routing
message so finding tickets land under it automatically.
Present a summary to the user:
Epic: <title>
Tickets: N total, M ready (unblocked), K in-progress, J closed
Ready tickets:
[<id>] <title>
[<id>] <title>
...
Blocked tickets:
[<id>] <title> (blocked by: <dep-ids>)
...
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.
- 2d ago First seen · 988 lines · 64 tokens per session scan A 1991de795bd2
run-epic is a skill published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 10,222 once invoked, about $0.0003 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…