Borrowing it
Nothing to install: this file belongs to alecs5am/ralphy. 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/alecs5am/ralphy/main/.agents/skills/dev-tasks/SKILL.mdgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/dev-tasks)<a href="https://agentmods.dev/skills/alecs5am/ralphy/dev-tasks"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/dev-tasks/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/alecs5am/ralphy/dev-tasks"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/dev-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 22 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00278 | $0.02199 |
| Opus 5.5 | $0.00111 | $0.00880 |
| Sonnet 5.5 | $0.00056 | $0.00440 |
| Haiku 4.5 | $0.00028 | $0.00220 |
Grade A, and why
dev-tasks 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-tasks — the capture-inbox manager for Ralphy dev work
This is a maintainer skill. It does not touch .ralphy/workspaces/<ws>/projects/ or call media models. It curates the notes/ capture inbox that tracks Ralphy's own development. notes/ is the only tracker — there is no separate roadmap board.
- Inbox —
notes/ideas/,notes/issues/,notes/decisions/. Free-form, monotonic-numbered (NNN-slug.md). The landing zone for any dev thought. notes/issues/is the live backlog, status-by-folder: flat top level = active,done/= resolved/landed,deprecated/= superseded/won't-do.
The contract lives in notes/README.md. Read it before your first capture or move in a session — this skill is the operator, that file is the law.
Division of labor with dev-issues / dev-loop
- This skill (
dev-tasks) ownsideas/+decisions/capture and the cross-inbox collision check. dev-issuesowns thenotes/issues/backlog: decomposing a brain-dump into well-shaped issue files, shaping them, filing/updating them. Read.agents/skills/dev-issues/SKILL.mdbefore doing any non-trivial issue work — don't duplicate its job here.dev-loopowns issue execution (pick → implement → move todone/).
When a captured idea matures into something actionable, promote it into a notes/issues/ item (per notes/README.md) and hand the shaping/execution to dev-issues / dev-loop.
Trigger
Hard triggers (always act):
- User types
/dev-tasks. - "log this / file this / capture this" + an idea, bug, or design thought about Ralphy itself.
- "record this decision" / "promote this note".
- "what's in the inbox" / "what's open".
- "is there already a note/idea for X" → run the collision check and report.
ALSO FIRE (proactively, offer — don't auto-execute)
- The user surfaces a design idea mid-dev-session and moves on without filing it → offer to capture it before it's lost.
- A note in
notes/ideas/has clearly matured (concrete acceptance criteria, no open questions) → offer to promote it into anotes/issues/item.
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 · 113 lines · 278 tokens per session scan A 76c85476cc00
dev-tasks is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 278 tokens to every session and 2,199 once invoked, about $0.0011 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
gini-bug-report
File a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill.
github-issues
Create, search, triage, label, assign, comment on, and close GitHub issues using the gh CLI, with a curl REST fallback.
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
linear
Read and write Linear issues, comments, projects, cycles, users, documents, initiatives, milestones, and more via the Linear MCP server. Attach chat-uploaded screenshots to issues.
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.