Borrowing it
Nothing to install: this file belongs to lukas-grigis/ralphctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lukas-grigis/ralphctl/main/.claude/skills/flow-trace-sync/SKILL.mdgit clone --depth 1 https://github.com/lukas-grigis/ralphctlWrote 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/lukas-grigis/ralphctl/flow-trace-sync)<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/flow-trace-sync"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/flow-trace-sync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/flow-trace-sync"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/flow-trace-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00162 | $0.01169 |
| Opus 5.5 | $0.00065 | $0.00468 |
| Sonnet 5.5 | $0.00032 | $0.00234 |
| Haiku 4.5 | $0.00016 | $0.00117 |
Grade A, and why
flow-trace-sync 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 2mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow Trace Sync
A ralphctl flow is a tree of named chain elements (sequential('implement', […]), guard('task-runnable-<id>', …), loop('task-attempts-<id>', …)). The order and names of those elements are the flow's observable shape —
and several docs describe it in prose or diagrams: the implementFlow example in KERNEL-DESIGN.md, the
sequence diagrams under .claude/docs/diagrams/, and the step-by-step criteria in REQUIREMENTS.md.
The code owns that shape in two places: the flow definition (the leaf/sequential/guard/loop('<name>')
calls) and the step-order fence test (which asserts trace.map(s => s.elementName) for happy + failure
paths — a test fails the moment the real order changes). The docs do not fail when they fall behind. So a
guard gets added, an element gets renamed, the loop nesting changes — the test is updated, the prose is not,
and the next reader trusts a sequence the harness no longer runs. This skill closes that gap.
When this earns its keep
- Right after you change a flow's element list — add/remove/reorder/rename a
leaf/sequential/guard/loop. - Before a release, alongside
drift-sweep, so the architecture docs ship accurate. - When a documented "A → B → C" trace looks wrong against the code.
How to run it
-
Extract the real element sequences:
bash .claude/skills/flow-trace-sync/scripts/flow-traces.sh # all flows bash .claude/skills/flow-trace-sync/scripts/flow-traces.sh implement # one flowFor each flow it lists the element names found in the definition (deduped, file order) and points at the fence test that asserts the canonical runtime sequence. Note: the listed order is definition order across files, not the exact runtime order — the fence test is authoritative for the precise sequence, so open it when order matters.
-
Locate the documented traces that describe the changed flow:
KERNEL-DESIGN.md— worked flow examples (e.g.implementFlow)..claude/docs/diagrams/— the sequence / lifecycle diagrams.REQUIREMENTS.md— criteria that spell out an attempt/loop body order.
What ships with it
1 file 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.
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.
- 2mo ago First seen · 67 lines · 162 tokens per session scan A a7e7bc8c8252
flow-trace-sync is a skill published in the GitHub repository lukas-grigis/ralphctl (24 stars, last pushed 4d ago), licensed MIT. It adds 162 tokens to every session and 1,169 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
flow-trace-sync compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flow-trace-synclukas-grigis/ralphctl | Skill | 24 | 4d ago | MIT | A | 162 | Claude Code |
| save-learningcaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 71 | Claude Code, Codex |
| reviewdevoxx/DevoxxGenieIDEAPlugin | Skill | 687 | yesterday | MIT | A | 90 | Claude Code |
| web-accessopen-octo/octo-agent | Skill | 141 | 2d ago | MIT | A | 139 | Claude Code, Codex |
| skill-creatoropen-octo/octo-agent | Skill | 141 | 2d ago | MIT | A | 123 | Claude Code, Codex |
| repothewaltero/mythos-router | Skill | 304 | yesterday | MIT | A | 11 | Claude Code, Codex |
| atomic-tdddamusix/atomic-claude | Skill | 115 | 5d ago | MIT | A | 142 | Claude Code, Codex |