add-tech

A project-extension guide for adding technical concerns to an agent codebase. It covers command lanes, repeatable clerical tasks, and hook policies, where hooks are automatic checks that run at defined points.

In plain words
What is it for?
Use it to add formatters, linters, release gates, deeper test levels, deterministic routine tasks, or policies that should run automatically.
Why use it?
It helps turn a missing project need into the right kind of reusable configuration instead of handling it manually each time.

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

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 946 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 $0.00020 $0.00946
Opus 5 $0.00010 $0.00473
Sonnet 5 $0.00004 $0.00189
Haiku 4.5 $0.00002 $0.00095

Measured 2d ago against content hash 1e37516e098f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-tech 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 2d 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/add-tech/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

add-tech

Role: the tech meta-skill. Add a non-language concern the descriptor does not cover: a lane entry, a spine task, or a hook policy. Generate the matching artifact from its schema and wire it into the descriptor.

Prerequisites

~/.agentic-sdk/<project>/project.edn exists (run bootstrap-project first). A real project need the curated config does not cover: a new build target, a deterministic clerical task the model does by hand, or a policy that belongs in a hook rather than a prompt.

Procedure

Follow the shared add-* procedure in docs/design.md section 8.3: detect the gap, interview for the skeleton's variable slot, generate against the skeleton, wire into the descriptor, validate. The artifact kind depends on the gap.

  1. Detect the gap and classify it. One of three kinds:
    • Lane entry: a new command in :lanes :cheap, :wave, or :pre-land (a formatter, a linter, a release gate, a deep test tier).
    • Spine task: a new deterministic clerical task that joins the interface in skills/shared/references/spine.md. The model does it identically every time, so it earns promotion to the spine.
    • Hook policy: a new template in :hooks that enforces a policy at the tool boundary, the way format-on-write, deny-secrets, and require-tests-before-land do.
  2. Interview for the schema. Ask one batch of at most three questions for what the artifact's schema needs:
    • For a lane entry: the command, the tier (cheap, wave, pre-land), and what failure stops.
    • For a spine task: the invocation name and arguments, what it reads, what it writes, the invariant it owns, and the exit contract (one line on stdout, exit code). It must be pure and deterministic on the unambiguous cases and refuse with a structured escalation on the ambiguous ones.
    • For a hook policy: the trigger (PreToolUse or PostToolUse, on which tools), the check, and the deny or warn action.
  3. Generate the artifact.
    • For a lane entry: no new file; the command lands in the descriptor.
    • For a spine task: author the task entry against the interface in spine.md. It joins the five stable names (triage, integrate, run, compile-rules, lint) or extends the catalog with a new name that answers the same contract shape.
    • For a hook policy: author the hook template into the toolkit's hook templates, parameterized by the descriptor.
  4. Wire the descriptor. Add the lane command to :lanes, the spine task name to the spine adapter, or the hook key to :hooks. The descriptor is the single tuning valve; the artifact is dead config without a descriptor entry.
  5. Validate. Run the artifact once dry: the lane command green on a clean tree; the spine task run on a sample input with the expected exit contract; the hook policy firing on a sample trigger and passing on a clean one. Tune from what the validation surfaced.
  6. Land. One commit, category Skills: (or Build: for a pure lane addition).

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 20 tokens per session scan A 1e37516e098f

Subscribe to this mod's changes

add-tech is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 946 once invoked, about $0.0001 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