skdd-hooks

skdd-hooks is a command for coding agents from zakelfassi/skills-driven-development. It costs 23 tokens per session (460 once invoked), scanned A, original, MIT.

Project settings for turning SkDD enforcement hooks on or off. These hooks act as checkpoints that can stop a coding session when its work is not properly finished or checked.

In plain words
What is it for?
Use it to enable, disable, or check the status of the finish-the-loop and freeze-the-session gates for a project.
Why use it?
They help prevent a session from ending with unverified claims or without a final review of what changed. The settings are kept per project and can be excluded from version control.

Command

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 commands/zakelfassi/skills-driven-development/skdd-hooks
Clone the repo
git clone --depth 1 https://github.com/zakelfassi/skills-driven-development

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 skdd-hooks

README.md
[![agentmods](https://agentmods.dev/badge/commands/zakelfassi/skills-driven-development/skdd-hooks.svg)](https://agentmods.dev/commands/zakelfassi/skills-driven-development/skdd-hooks)
Your own site
<a href="https://agentmods.dev/commands/zakelfassi/skills-driven-development/skdd-hooks"><img src="https://agentmods.dev/badge/commands/zakelfassi/skills-driven-development/skdd-hooks.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 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 $0.00023 $0.00460
Opus 5 $0.00012 $0.00230
Sonnet 5 $0.00005 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 3d ago against content hash 36f668857737, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skdd-hooks 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 3d 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.

plugins/skdd-claude/commands/skdd-hooks.md · 38 lines

What it actually says

Manage the SkDD enforcement hooks for this project. The hooks are off by default and their state lives in .claude/skdd.local.md (project-scoped, survives sessions; add it to .gitignore if the team shouldn't share it).

The user's request: $ARGUMENTS

What to do

  1. Read .claude/skdd.local.md if it exists. Its frontmatter holds the toggles:

    ---
    skdd-hooks:
      finish-the-loop: false
      freeze-the-session: false
    ---
    
    # SkDD hook toggles
    
    Managed by /skdd-claude:skdd-hooks. `true`/`on` enables a gate for this project.
    
  2. Apply the request:

    • on / off (no gate named) → set both gates to that state.
    • finish-the-loop on|off or freeze-the-session on|off → set just that gate.
    • status or empty → don't write anything; report the current state of both gates.
  3. Write the file back (create .claude/ if needed, keep the format above — the hook scripts parse the gate-name: true|false lines).

  4. Confirm to the user what changed, and remind them what each gate does:

    • finish-the-loop (Stop gate): if the session changed product source and the final report claims success without observed evidence ("should work now"), the stop is bounced once with instructions to verify or state plainly that it's unverified. Second stop always passes.
    • freeze-the-session (SessionEnd + PreCompact reminder): if the session looks substantive and the colony registry hasn't been touched, a non-blocking reminder to extract skills/conventions before the context dies.

A skill is a procedure the model follows when it decides to; a hook is a gate for when it forgets.

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. 3d ago First seen · 38 lines · 23 tokens per session scan A 36f668857737

Subscribe to this mod's changes

skdd-hooks is a command published in the GitHub repository zakelfassi/skills-driven-development (18 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 460 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 2026-08-30.