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/jepegit/issue-flow/iflownpx skills add jepegit/issue-flow --skill iflowgit clone --depth 1 https://github.com/jepegit/issue-flowWhat 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 | $0.00036 | $0.02184 |
| Opus 5 | $0.00018 | $0.01092 |
| Sonnet 5 | $0.00007 | $0.00437 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
iflow 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
issue-flow — iflow smart dispatcher (/iflow)
Follow this skill to run the right next step in the issue-flow lifecycle: it detects state and routes to /iflow-init, /iflow-plan, /iflow-build, or /iflow-close, forwarding trailing args verbatim.
Do not use this skill for /iflow-pick, /iflow-pause, /iflow-cleanup, /iflow-yolo, /iflow-fix, /iflow-issue, /iflow-split, /iflow-review, or other off-path helpers. Those are explicit-only commands. (/iflow-pick is the front door before /iflow-init, for when no issue has been chosen yet. /iflow-fix runs an interactive iterative-fixes session, driven by /iflow-fix + /iflow-close. /iflow-issue creates one well-specified normal GitHub issue. /iflow-split cuts an over-large issue into linked sub-issues.)
Invoke: type iflow in chat, or /iflow from the slash menu.
MODEL & EXECUTION DIRECTIVE
Profile: economy — Prioritize speed and token economy over deep reasoning.
In Cursor: use Auto or a fast model before invoking this step.
Keep scope tight to what this step requires.
Resolve project root (multi-root workspaces)
Before any git, gh, or .issueflows/ path operation in this workflow:
Resolution order (stop when unambiguous):
- Explicit hints in slash input —
root:<path>,repo:<folder-basename>(directory name, e.g.cellpy-core), orrepo:owner/name. - CLI fast path —
issue-flow agent resolve [-C <start>] [--from-file <active-file>] [--json]. Use the returnedproject_rootandrepo; pass-C <project_root>to otherissue-flow agent …subcommands. When the answer came from the workspace registry, the payload setsresolved_via_workspace_default: true. - Branch context — exactly one workspace repo whose branch matches
^\d+-→ that root. - Single scaffold — exactly one
.issueflows/tree visible in the workspace → that root. - Workspace default — an
issueflow-workspace.tomlat the workspace root (created withissue-flow workspace init) may name adefaultmember repo; use it when no scaffold matched above. Tell the user the default was used. - Ambiguous → stop and ask; never guess between sibling repos.
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 · 110 lines · 36 tokens per session scan A 946b89015695
iflow is a skill published in the GitHub repository jepegit/issue-flow (4 stars, last pushed 19d ago), licensed MIT. It adds 36 tokens to every session and 2,184 once invoked, about $0.0002 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…