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 agentmods add skills/izkreny/agentifico/implementnpx skills add izkreny/agentifico --skill implementgit clone --depth 1 https://github.com/izkreny/agentificoWhat 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 | $0.00114 | $0.02210 |
| Opus 5 | $0.00057 | $0.01105 |
| Sonnet 5 | $0.00023 | $0.00442 |
| Haiku 4.5 | $0.00011 | $0.00221 |
Grade A, and why
implement 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tools used: bare
Bashrather than a narrowed list, because this is the one skill in the flow that runs the repository's own commands - tests, linters, builds - and those cannot be enumerated here;ghandgitcarry the PR and branch work inside it.Read/Write/Edit/Grep/Globcarry the code itself;TodoWritemirrors the plan's## Stepsinto the session todo list during implementation;EnterWorktreemoves the session into the branch's worktree where the owner keeps one.
The user invoked this skill with the argument: $ARGUMENTS
This is a routing skill. Read $ARGUMENTS, pick exactly one workflow per Routing below, and follow it inline, in this session.
Implementation runs in the session that holds the context for it. That session has read the plan, or has heard which findings the owner said stand, and it knows why the code is shaped as it is. It will not undo something deliberate the way a cold agent does, and it does not have to be told in a prompt what it already knows. Never hand this work to a subagent, and never summarise a workflow's handoff: the handoff is the record, and it is printed as the workflow wrote it.
Settling the plan record is the first act of workflows/implement.md Step 1 rather than something done before starting, because there is no before. A fix never does it: the review protocol in the pr-flow skill owns that state, unpushed.
All paths below are relative to this skill's own directory. Resolve them against wherever this skill is installed rather than assuming a location.
Every file here is written to the agent, so you is the agent reading it. The human is the owner, always in the third person - the same voice rule as pr-flow, and for the same reason. The exception is README.md, which the owner reads rendered and which addresses them directly.
Where this sits
This skill is the implementation stage of a branch's life, the node the pr-flow and tracker lifecycle diagrams name implement. Everything around it stays there: open created the draft PR this skill requires, ready audits what this skill leaves behind, review and merge come later. You never do their work from here - never lift the draft, never post a review, never merge.
It is also written to be resumable across sessions: all state lives on the PR and the branch - ticked boxes, commits - and none in the session. A fresh session picks up mid-implementation by reading that state, which is what workflows/implement.md Step 2 does.
What ships with it
3 files 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.
- yesterday First seen · 59 lines · 114 tokens per session scan A f56b581a96d2
implement is a skill published in the GitHub repository izkreny/agentifico (2 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 2,210 once invoked, about $0.0006 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.