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 xobotyi/cc-foundry --skill tasksgit clone --depth 1 https://github.com/xobotyi/cc-foundryWrote 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/xobotyi/cc-foundry/tasks)<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/tasks"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/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/xobotyi/cc-foundry/tasks"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 12 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 | $0.00049 | $0.01480 |
| Opus 5.5 | $0.00020 | $0.00592 |
| Sonnet 5.5 | $0.00010 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasks
Decompose frame phases into work items an implementer can pick up without asking questions. Each frame phase becomes a
group of tasks; each task is sized, dependency-mapped, and given a verifiable artifact. The breakdown feeds
task-creation, which owns what a written work item contains — this skill owns how the work is cut up.
Prerequisites
Locate the inputs:
- Frame — check conversation context first; fall back to
design-docs/NN-name.frame.md; if absent, ask whether to run frame. - Alignment — optional reference for pattern decisions and ADRs. Check context or disk.
Process
Phase 1 — Draft Task Table
- Read the frame document's phases, components, acceptance criteria, and phase sequence.
- For each phase, identify the individual work items within it. A phase may produce 1–7 tasks. If a phase needs more than 7, it's likely too coarse — reconsider splitting the phase in the frame.
- For each task, write:
- Title (
task-creationowns what a title looks like) - Estimate (hours — enough to validate sizing, not a commitment)
- Dependencies (other tasks that must complete first)
- Artifact (expected output: file path, passing test, endpoint, or other verifiable result)
- Mode: AFK (agent can execute autonomously) or HITL (requires human at keyboard — alignment, QA, taste)
- Parent phase
- Title (
- Present as a grouped table. Validate the structure before investing in detailed descriptions.
Ask the user for approval of the draft table before proceeding.
Phase 2 — Validate Sizing
Verify every task against the sizing guidance:
- Over 8 hours: Break down further. No exceptions. If it can't be split, the work isn't understood well enough.
- 6–8 hours: Acceptable but check for a natural seam.
- 2–4 hours: Sweet spot. Clean boundaries, estimable with confidence.
- Under 1 hour: Combine with related tasks unless isolation matters for risk or dependency reasons.
- Can't estimate: Go back to the frame or investigate the codebase.
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 · 148 lines · 49 tokens per session scan A 14fa50e39dca
tasks is a skill published in the GitHub repository xobotyi/cc-foundry (22 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 1,480 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
remove
Remove a deployed framework or addon from the current workspace.