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/jakkaj/tools/the-flownpx skills add jakkaj/tools --skill the-flowgit clone --depth 1 https://github.com/jakkaj/toolsWrote 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/jakkaj/tools/the-flow)<a href="https://agentmods.dev/skills/jakkaj/tools/the-flow"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/the-flow.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00252 | $0.04898 |
| Opus 5 | $0.00126 | $0.02449 |
| Sonnet 5 | $0.00050 | $0.00980 |
| Haiku 4.5 | $0.00025 | $0.00490 |
Grade A, and why
the-flow 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/the-flow — SDD pipeline dispatch
One public skill for the whole SDD pipeline, built to the flow-architecture pattern (docs/skills-pipeline/flow-architecture.md): the sub-skills (contract-bound verbs, one per stage) live in references/stages/, the guided-mode engine in references/00-routing.md, the coaching voice in references/coach.md. New to the flow? references/getting-started.md.
Progressive disclosure is the contract: load exactly one sub-skill for the current step — never read all of them up front.
Two load paths
Guided — /the-flow (no args, or <slug> / <ord>-<slug>):
- Read
references/00-routing.md(entry paths, state contract, the Graph) andreferences/coach.md(rail, narration, print-then-offer). - Resolve fresh / resume / adopt per 00-routing.md; load only the current stage's sub-skill when a step is accepted, and coach the seam.
- Guided mode owns all the-flow state, and drives all of it — position and session bag — through
harness flow navcalls: the flight plan (the-flow.json→the-flow.md) is the single state substrate (plan 024 — the CLI is the generator; nothing is hand-written; run the capability precheck first, § Prerequisite). Before the first flight-plan mutation of a session, also loadreferences/flight-plan-ops.md— the nav model, the spine-vs-excursion rule, and the verb flags + gotchas (loaded on demand, not up front; sub-skills never load it).
Direct jump — /the-flow <id> <verb> [flags]:
- Resolve the stage via the Registry below. Id and verb each resolve alone (typing
6≡ typingimplement); when both are given they must name the same stage — if they disagree, show the Registry and ask which was meant (never guess). - Read only that sub-skill and follow it with the given flags (same flags the verb has always taken).
- No coach, no rail, no state writes — and no harness seams (harness orchestration is the guided engine's job — direct-jump runs the bare verb, harness-less by design). Artifacts land where they always did; the next guided run discovers them by existence and catches state up.
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/00-routing.md 42 KB
- references/coach.md 42 KB
- references/flight-plan-ops.md 9.4 KB
- references/flight-plan.example.json 11 KB
- references/flight-plan.example.md 4.7 KB
- references/flight-plan.schema.json 3.6 KB
- references/flight-plan.template.json 8.5 KB
- references/getting-started.md 20 KB
- references/harness-seams.md 32 KB
- references/stages/10-explore.md 15 KB
- references/stages/20-plan.md 36 KB
- references/stages/25-workshop.md 26 KB
- references/stages/35-adr.md 21 KB
- references/stages/50-phase-tasks.md 13 KB
- references/stages/60-implement.md 20 KB
- references/stages/62-progress.md 9.3 KB
- references/stages/70-review.md 17 KB
- references/stages/80-merge.md 30 KB
- references/stages/80-ship.md 15 KB
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.
- 4d ago First seen · 115 lines · 252 tokens per session scan A 34a961e4e122
the-flow is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 18d ago), licensed MIT. It adds 252 tokens to every session and 4,898 once invoked, about $0.0013 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…