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 Enakoneschniy/claude-dev-stack --skill budget-continuegit clone --depth 1 https://github.com/Enakoneschniy/claude-dev-stackWrote 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/enakoneschniy/claude-dev-stack/budget-continue)<a href="https://agentmods.dev/skills/enakoneschniy/claude-dev-stack/budget-continue"><img src="https://agentmods.dev/badge/skills/enakoneschniy/claude-dev-stack/budget-continue/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/enakoneschniy/claude-dev-stack/budget-continue"><img src="https://agentmods.dev/badge/skills/enakoneschniy/claude-dev-stack/budget-continue.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 | $0.00064 | $0.00706 |
| Opus 5.5 | $0.00026 | $0.00282 |
| Sonnet 5.5 | $0.00013 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
budget-continue 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Continue Skill
When the session budget warning fires, this skill presents a 4-option continuation menu and (when invoked inside a Claude Code session) can schedule the appropriate follow-up action using native Claude Code tools.
Invocation
claude-dev-stack budget continue
Or invoke this skill directly: /budget-continue
The 4 Options
Option 1: Remind me later (CronCreate)
Creates a one-shot CronCreate reminder that fires in the current Claude Code session after a delay.
When the user selects this option inside a Claude Code session:
Use CronCreate to schedule a reminder:
Title: "Resume GSD session — budget warning"
Prompt: "/budget-continue"
Schedule: "+1h" (or user-chosen delay)
Repeat: false
Option 2: Auto-continue locally (Desktop task)
Creates a Desktop task that fires on the local machine after a delay and runs the GSD resume workflow.
When the user selects this option inside a Claude Code session:
Use the Desktop task tool:
Prompt: "/gsd-resume-work"
Schedule: "+1h" (or user-chosen delay)
Note: The machine must be on when the task fires. STATE.md is read to determine what to resume.
Option 3: Auto-continue in cloud (Cloud task)
Creates a Cloud task that runs on Anthropic infrastructure. Performs a fresh git clone and runs the GSD resume workflow autonomously — works even when the local machine is off.
When the user selects this option inside a Claude Code session:
Use the Cloud task tool:
Repo: (git remote origin URL — auto-detected)
Prompt: "/gsd-resume-work"
Schedule: "+1h" (or user-chosen delay)
Note: All state must be committed to git. GSD guarantees this via STATE.md.
Option 4: Continue now
No scheduling action. Prints a message to continue with the current session. Useful if the user decides to keep working and address the budget limit later.
What the scheduled task runs
Both Desktop and Cloud tasks run /gsd-resume-work, which reads .planning/STATE.md:
- If
stopped_atis present: resumes from that point usingresume_fileas context - If no stopped work: runs maintenance tasks (check PRs,
/gsd-next,/gsd-health)
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 · 85 lines · 64 tokens per session scan A dfade9da9913
budget-continue is a skill published in the GitHub repository Enakoneschniy/claude-dev-stack (5 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 706 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
behavior-design
Use when a goal must be converted into a repeatable behavior, cue, SOP, review cadence, and identity-aligned reinforcement.
daily-okr
Use when planning or closing a daily knowledge-compounding cycle across input, cognition, wiki, behavior, creativity, output, and feedback.
treat
Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
reload
Treat the current session and auto-resume in a new terminal window.