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 skills add mike-coulbourn/claude-vibes --skill graph-runninggit clone --depth 1 https://github.com/mike-coulbourn/claude-vibesWrote 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/mike-coulbourn/claude-vibes/graph-running)<a href="https://agentmods.dev/skills/mike-coulbourn/claude-vibes/graph-running"><img src="https://agentmods.dev/badge/skills/mike-coulbourn/claude-vibes/graph-running/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/mike-coulbourn/claude-vibes/graph-running"><img src="https://agentmods.dev/badge/skills/mike-coulbourn/claude-vibes/graph-running.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00105 | $0.01316 |
| Opus 5.5 | $0.00042 | $0.00526 |
| Sonnet 5.5 | $0.00021 | $0.00263 |
| Haiku 4.5 | $0.00011 | $0.00132 |
Grade A, and why
graph-running 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph running
Run an approved graph the way it was drawn. The graph-engineering skill designs the work and stops at approval. This skill picks up from there.
Start only from an approved graph
You need three things from graph-engineering before you begin: the confirmed alignment contract, the graph with each job's owner and output, and the user's approval of that graph. If any is missing, go back to claude-vibes:graph-engineering. Do not improvise a graph here, because a graph nobody approved has no authority to guide the work.
Approval of the graph is not approval of every step in it. Each human gate in the graph still needs its own yes at the moment the work reaches it.
Save the graph before running it
If the approved graph recommends manual lanes, a shared note the user keeps is enough. Otherwise write the graph to a file first, so the work survives a closed session and anyone can see what was decided and why.
- A whole-project graph lives in
docs/01-START/roadmap.md, which the04-plan-roadmapcommand writes and the05-track-progresscommand maintains. Use that file's format and do not create a second one. - Any other graph goes in
docs/graphs/<short-name>.md, with these sections: the alignment contract, the diagram, a checklist with one line per job (owner, what it depends on, its output, any gate), a "State" section that collects each job's result, and a dated change log.
Run date +%Y-%m-%d before writing a date.
Run the jobs
- Follow the arrows. A job starts only when every job it depends on has finished and its output is in the State section.
- Run independent lanes the way the graph says. Use the execution level the approved graph recommends. At manual lanes, walk the user through one job at a time and carry the state yourself. At file trails, run each job in turn and record what it produced. At an orchestrated graph, launch independent lanes as separate subagents in a single message with the Agent tool. If the graph names no level, start with file trails and ask before automating further. Lanes that share no arrow must not wait on each other, and they must not see each other's drafts, or they stop being independent.
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.
- 1mo ago First seen · 60 lines · 105 tokens per session scan A 262776a0fa99
graph-running is a skill published in the GitHub repository mike-coulbourn/claude-vibes (44 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,316 once invoked, about $0.0004 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 2026-09-22.
Other skills, from other repositories
customer-success-management
Runs the ongoing relationship with accounts after the sale — segmenting coverage against account value, building a health score that predicts rather than describes, running reviews customers find worth attending, forecasting renewals honestly, and finding expansion that follows usage instead of quota. Use this to…
chief-information-officer
The CIO's remit — running the technology the company works on, service quality, IT spend, and the boundary with product engineering. Use this to set IT priorities, decide what IT owns versus engineering, structure IT spend or an IT roadmap, judge whether to build, buy or outsource, or work out why IT is seen as a cost…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
chief-operating-officer
Owns execution: how work actually gets done across the organization, including process, program management, capacity, vendors, supply chain, and service delivery. Use this when execution is the problem rather than strategy, to design or fix a process, to resolve cross-functional handoff failures, to plan capacity, to…
incident-management
Runs an operational incident from detection to closed action — declaring it and naming a commander, separating the people restoring service from the people communicating, keeping a timeline as it happens, deciding when it is over, and running a review that produces a small number of changes someone actually completes.…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…