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 alunduil/alunduil-chezmoi --skill dfdgit clone --depth 1 https://github.com/alunduil/alunduil-chezmoiWrote 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/alunduil/alunduil-chezmoi/dfd)<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/dfd"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/dfd/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/alunduil/alunduil-chezmoi/dfd"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/dfd.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 | $0.00080 | $0.01232 |
| Opus 5 | $0.00040 | $0.00616 |
| Sonnet 5 | $0.00016 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
dfd 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 12d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DFD
References:
- https://miro.com/diagramming/what-is-a-data-flow-diagram/ — components, levels, logical vs physical.
- https://www.visual-paradigm.com/guide/data-flow-diagram/what-is-data-flow-diagram/ — drawing rules, balancing.
A DFD shows where data moves and what transforms it. Sequencing belongs in a flowchart, object structure in UML; a DFD carries neither. Control signals are not data — leave them out.
Components
Four, and only four:
| Component | Is | Gane–Sarson | Yourdon/DeMarco | Mermaid |
|---|---|---|---|---|
| External entity | A source or sink outside the system boundary | square | rectangle | E[Name] |
| Process | Work that transforms input data into output data | rounded rectangle | circle | P(1.0 Verb the thing) |
| Data store | Data at rest — a file, table, queue, keyring | open-ended rectangle | two parallel lines | S[(Name)] |
| Data flow | Named data moving between the above | labelled arrow | labelled arrow | A -->|data name| B |
Name every element. Entities and stores take noun phrases, processes
take verb phrases, flows take the name of the data itself
(plaintext token), never the mechanism carrying it.
Levels
Each level decomposes one process from the level above.
- Context — the whole system as a single process numbered
0, surrounded by every external entity it exchanges data with. No data stores; internal storage is inside the system. - Level 0 — process
0opened up into its major processes, numbered1.0,2.0,3.0. Data stores appear here first. - Level 1 onward — one process from the level above opened up,
numbered beneath it. Decomposing
2.0gives2.1,2.2; decomposing2.1gives2.1.1.
Stop at the level that answers the question asked, or at a process whose decomposition would only restate it.
Pick logical or physical per diagram and hold it: a logical DFD names business activities, a physical one names the software, hosts, and files doing the work.
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.
- 12d ago First seen · 130 lines · 80 tokens per session scan A 81c676580363
dfd is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 80 tokens to every session and 1,232 once invoked, about $0.0004 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
batch-grill-me
A relentless interview that asks every frontier question at once, round by round.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
repo-activity
Scan all git repositories under /repos and report recent activity — last commit age, branch, uncommitted changes — in age-bucketed tables. Use when the user asks for a repo activity overview, "what have I been working on", portfolio status, or which repos are active/dormant.