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 commands/fakoli/fakoli-plugins/flowgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWhat 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 | $0.00044 | $0.00785 |
| Opus 5 | $0.00022 | $0.00392 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List all available fakoli-flow skills with their commands and purposes, display the workflow pipeline, then run detect-context.sh to show the current project state.
How invocation works
/fakoli-flow:flow (no suffix) is this menu — it shows what's available and the current project context, but does not run a skill. To run a skill, invoke it directly by name: /fakoli-flow:brainstorm, /fakoli-flow:plan, /fakoli-flow:execute, /fakoli-flow:verify, /fakoli-flow:finish, or /fakoli-flow:quick. The harness routes these to the matching skills/<name>/SKILL.md file. Arguments accepted by each skill (spec path, plan path, free-form task) are listed in the table below.
Skills
| Skill | Command | Purpose |
|---|---|---|
| Brainstorm | /fakoli-flow:brainstorm |
Design phase — refine ideas into specs through collaborative dialogue |
| Plan | /fakoli-flow:plan |
Plan phase — break approved specs into intent-driven task lists for crew execution |
| Execute | /fakoli-flow:execute |
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification |
| Verify | /fakoli-flow:verify |
Verify phase — evidence-based validation with sentinel dispatch and pass/fail scorecard |
| Finish | /fakoli-flow:finish |
Ship phase — merge, PR, keep, or discard with pre-merge verification |
| Quick | /fakoli-flow:quick <task> |
Fast path — skip the full workflow for small tasks under 3 files |
Workflow
brainstorm → plan → execute → verify → finish
↑
quick ──┘ (skips brainstorm, plan, and execute waves)
quick is the fast path for bug fixes, parameter changes, and typo corrections.
Use the full pipeline when you need a spec, want wave-based parallelism, or the
change touches 3+ files.
Project State
The SessionStart hook runs detect-context.sh automatically when a session begins and
prints the detected language and crew availability to the session context. Running /fakoli-flow:flow
re-detects context on each invocation, so the output always reflects the current project
state — no need to scroll back to the start of the conversation.
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 · 80 lines · 44 tokens per session scan A 448c9f4648d5
flow is a command published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 24d ago), licensed MIT. It adds 44 tokens to every session and 785 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 commands, from other repositories
psalm
Command "psalm" from Marcel-Bich/marcel-bich-claude-marketplace, covering credo - the preacher's guide, step 0: run setup (recommended), entry point, credo's own teachings and topic: the credo workflow (end to end).
docs-update
You are executing the /dogma:docs-update command. Your task is to synchronize documentation across README files and wiki articles, ensuring everything is up-to-date.
sanitize-git
You are executing the /dogma:sanitize-git command. Your task is to find and remove AI/Claude traces from git history and fix tracking issues where files that should be excluded are still being tracked.
session-init
You are the Main Agent in an orchestrated workflow. Read and internalize these working instructions.
permissions
Create or update DOGMA-PERMISSIONS.md to configure what Claude can do autonomously.
versioning
Universal version file discovery and sync. Works with any project structure.