maintain-toolchain

maintain-toolchain is a skill for Claude Code, Codex from leifericf/agentic-sdk. It costs 39 tokens per session (997 once invoked), scanned A, original, MIT.

A skill for maintaining a project's pinned programming tools and checking that the installed versions match those pins. A toolchain is the set of compilers, interpreters, and related development tools used to build software.

In plain words
What is it for?
Use it to diagnose version mismatches, enforce the project's pinned versions, safely bump them, and retain the known investigated limit for checks.
Why use it?
It prevents a developer's machine from silently using a different tool version and producing misleading build results.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/leifericf/agentic-sdk/maintain-toolchain
Any agent
npx skills add leifericf/agentic-sdk --skill maintain-toolchain
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for maintain-toolchain

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/maintain-toolchain.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/maintain-toolchain)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/maintain-toolchain"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/maintain-toolchain.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 997 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00997
Opus 5 $0.00019 $0.00498
Sonnet 5 $0.00008 $0.00199
Haiku 4.5 $0.00004 $0.00100

Measured 4d ago against content hash 70a71e270a23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maintain-toolchain 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 4d 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.

skills/maintain-toolchain/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maintain-toolchain

Role: keep the toolchain pinned, diagnosed, and bumped, and keep the investigated ceiling from being re-spiked.

One law: the pin is the pin. Every lane runs the pinned toolchain and only the pinned toolchain. The pin lives in the descriptor (the :lanes commands assume it) and in the language-native pin files (.zig-version plus build.zig.zon's minimum_zig_version for Zig; .tool-versions or per-language version files for other stacks; lockfiles where the language uses them). Never substitute a host toolchain of a different version to make a lane pass. That is an infrastructure failure to report, not to work around.

The doctor check

A doctor lane diagnoses the toolchain: it reads the pin, runs the host's version command, and compares. It reports the resolved path, the running version, the pinned version, and whether they match. Run it first when a lane reports a toolchain problem. The doctor command is itself a lane in the descriptor's table (commonly under :pre-land or a :doctor slot the verifier runs on demand); it is not hardcoded here.

How lanes report the pin

A lane whose pinned toolchain is absent or mismatched hard-fails; it never silently passes on a different version. The line is exactly:

FAIL <lane>: pinned <tool> missing (repro: <doctor command>)

This applies to every lane in the table; the tier verdict is then VERDICT: FAIL. Diagnose with the doctor check before touching anything else; a missing pin is fixed by installing the pinned toolchain, not by loosening the pin.

The bump ritual

A pin bump is deliberate and lands as its own commit.

  1. Update every pin site in lockstep: the descriptor, the language- native version files, the CI workflow's setup action, and any lockfile. Identical version in every site, one change.
  2. Regenerate whatever the toolchain produces (stencils, bindings, generated headers, format baselines) and commit the regeneration in the same change.
  3. The doctor check must report a match; the full lane table (all three tiers) must pass on the new pin before the bump commits.
  4. Commit alone, category-first subject (for example Build: Bump pinned toolchain), no version number in the message.

Read the full file on GitHub · 97 lines

Changes

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.

  1. 4d ago First seen · 97 lines · 39 tokens per session scan A 70a71e270a23

Subscribe to this mod's changes

maintain-toolchain is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 997 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens