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 wunki/dotfiles --skill devloggit clone --depth 1 https://github.com/wunki/dotfilesWrote 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/wunki/dotfiles/devlog)<a href="https://agentmods.dev/skills/wunki/dotfiles/devlog"><img src="https://agentmods.dev/badge/skills/wunki/dotfiles/devlog/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/wunki/dotfiles/devlog"><img src="https://agentmods.dev/badge/skills/wunki/dotfiles/devlog.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 | $0.00089 | $0.01746 |
| Opus 5.5 | $0.00036 | $0.00698 |
| Sonnet 5.5 | $0.00018 | $0.00349 |
| Haiku 4.5 | $0.00009 | $0.00175 |
Grade A, and why
devlog 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devlog
Update the project's DEVLOG.md so it captures what the user did, learned, decided, and where to continue next. Also use DEVLOG.md to help the user jump back into a project by summarizing recent context and recommending the next concrete action.
This is not a generic changelog. It is a personal working journal with concrete shipped details and reflective notes. Treat it as both an end-of-session memory and a start-of-session handoff.
Discovery
- Find the target devlog:
- Prefer an explicitly referenced
@DEVLOG.md/ path from the user. - Otherwise use
DEVLOG.mdin the current working directory. - If no obvious target exists, search upward from
cwd; if still unclear, ask.
- Prefer an explicitly referenced
- Read the existing
DEVLOG.mdbefore writing. - Gather evidence from the real work:
git status --shortgit diff --statgit diffgit diff --cached- recent commits if relevant:
git log --oneline --decorate -5 - the current conversation/session context
- project docs or tests only when needed to understand the change
- Do not invent facts. If an important detail is missing, ask the user instead of filling it in.
Resume Workflow
Use this workflow when the user asks things like "where were we?", "catch me up", "resume this project", "what should I do next?", "read the devlog", or devlog resume.
- Find and read the target
DEVLOG.mdusing the discovery rules above. - Read the latest entry first. Include earlier entries only if they clarify context or the latest entry is too thin.
- Optionally inspect current repo state when useful:
git status --shortgit diff --stat- recent commits:
git log --oneline --decorate -5
- Summarize the current project state in the user's language:
- what was last shipped or made real
- what was learned
- decisions that still matter
- gotchas or blockers
- the current mental model, if one is present
- Extract the actionable continuation items, especially
NEXT,BLOCKED, andRESEARCHbullets. - Recommend the first concrete next action. Prefer one small step that can be started immediately.
- If repo state conflicts with the devlog, call that out plainly before recommending next steps.
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 · 202 lines · 89 tokens per session scan A ee66691c998c
devlog is a skill published in the GitHub repository wunki/dotfiles (47 stars, last pushed 10d ago), licensed MIT. It adds 89 tokens to every session and 1,746 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 2026-08-30.
Other skills, from other repositories
save-pipeline-memory
Capture a multi-step workflow into a timestamped pipeline memory after trial-and-error sessions. The core output is: (1) the final working commands saved as executable scripts (not bare shell commands), and (2) a structured markdown document separating the clean reproducible pipeline from the detours and pitfalls.…
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. Do NOT use for installing tools, running doctor, or updating a machine through the dotfiles CLI; use manage-machine.
taskgo
Maintains a private Git-backed personal project and task control repository using concise current Markdown, derived Git history, ADRs, and status synchronization. Use when tracking tasks, updating project status (STATUS.md), managing ADRs, synchronizing tracker state, handing tasks to agents, or generating…
handoff
Save state at the end of a session, or resume from the last one. Triggers "wrapping up", "running out of context", "done for today", "continue where we left off", "resume".
heap-snapshot-inspection
Investigating memory issues and leaks in Chromium-based environments (Chrome, Node.js, Electron) using heap snapshots and the @paulirish/agents CLI.
toil-offloading-pi
Orchestrate decomposable workloads with pi subagents (afang-subagent extension): the strong-but-slow root agent clarifies goals, cuts the work into contract-bearing subtasks, fans them out to cheap-and-fast subagents, grades delivery risk, runs an independent review where it pays, and accepts the result. Use when the…