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 mhylle/claude-skills-collection --skill tt-implement-phasegit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/tt-implement-phase)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/tt-implement-phase"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-implement-phase/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/mhylle/claude-skills-collection/tt-implement-phase"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-implement-phase.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 Agent Snooping · line 555 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.
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 | $0.00258 | $0.07875 |
| Opus 5 | $0.00129 | $0.03938 |
| Sonnet 5 | $0.00052 | $0.01575 |
| Haiku 4.5 | $0.00026 | $0.00788 |
Grade A, and why
tt-implement-phase scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| HTTP API | curl / httpie / fetch subagent against running server | How it starts
The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tt-implement-phase
Execute a single phase whose spec lives as a tasktracker phase task with sub-tasks. Designed to be called by /tt-implement-plan, but invokable directly when you want to drive one phase end-to-end.
How this differs from /implement-phase
/implement-phase |
/tt-implement-phase (this skill) |
|
|---|---|---|
| Phase spec source | Markdown plan file + phase number | Tasktracker phase task + sub-tasks |
| Sub-task tracking | Plan checkbox edits | tasktracker_updateTaskStatus per sub-task |
| Plan sync (Step 6) | Edit plan markdown | Verify sub-task statuses, no plan file to sync |
| Prompt archival (Step 7) | Move docs/prompts/*.md |
N/A — no prompt files |
| Phase notes during work | Edit plan section | New sub-task ("Decision: X") — phase body is locked |
| Active task | None | setActiveTask on phase + per-sub-task |
| Defects / learnings | Plan deviations section | logDefect, logLearning, logFriction |
| ADR linkage | Plan section + INDEX.md | Sub-task ADR-NNNN reference + INDEX.md |
| Code review (Step 4) | /code-review |
/code-review (unchanged) |
If the phase lives in a markdown plan file, use /implement-phase. If the phase is a tasktracker phase task, use this skill.
Execution mode — orchestrated vs in-context (decide at Step 0)
This skill has two execution modes — but orchestrated is the default and almost always the right one.
-
Orchestrated (the default). The
Agent(subagent-dispatch) tool is a top-level BUILT-IN of the main loop — likeBash/Read/Edit. This skill runs incontext: fork(the main loop), soAgentis ALWAYS available; there is nothing to detect. Offload code-writing, file-creation, test-running, and fixing to subagents (Agent, optionallyisolation: 'worktree') so the parent context stays lean. The rest of this doc is written in its voice. -
In-context (true last resort only). Do the work yourself with
Edit/Write/Bash+ the tasktracker MCP. Use this only if a direct attempt to dispatch anAgentactually errors — never on an inferred absence.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +5 lines 6d058165e423
- 10d ago First seen · 569 lines · 258 tokens per session scan A 4fe820cf0863
tt-implement-phase is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It adds 258 tokens to every session and 7,875 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.