deft-directive-spec-reconstruct

deft-directive-spec-reconstruct is a skill for Claude Code, Codex from deftai/directive. It costs 91 tokens per session (1,460 once invoked), scanned A, original, no licence file.

A method for rebuilding a software specification from an existing codebase and completed investigation briefs. It can also check whether the implementation has drifted from the intended specification, without automatically changing the specification.

In plain words
What is it for?
Use it to recover requirements from an older project, repair a failed or stale specification, and review differences between the code and its documented meaning.
Why use it?
It helps when requirements are missing, outdated, or no longer match an existing project. Draft-only results let a developer review proposed changes before accepting them.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to recover requirements from an older project, repair a failed or stale specification, and review differences between the code and its documented meaning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deftai/directive/deft-directive-spec-reconstruct
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.

Any agent
npx skills add deftai/directive --skill deft-directive-spec-reconstruct
Clone the repo
git clone --depth 1 https://github.com/deftai/directive

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 deft-directive-spec-reconstruct

README.md
[![agentmods](https://agentmods.dev/badge/skills/deftai/directive/deft-directive-spec-reconstruct/github.svg)](https://agentmods.dev/skills/deftai/directive/deft-directive-spec-reconstruct)
Your own site
<a href="https://agentmods.dev/skills/deftai/directive/deft-directive-spec-reconstruct"><img src="https://agentmods.dev/badge/skills/deftai/directive/deft-directive-spec-reconstruct/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.

agentmods 80×15 button for deft-directive-spec-reconstruct

Your own site · 80×15
<a href="https://agentmods.dev/skills/deftai/directive/deft-directive-spec-reconstruct"><img src="https://agentmods.dev/badge/skills/deftai/directive/deft-directive-spec-reconstruct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00091 $0.01460
Opus 5.5 $0.00036 $0.00584
Sonnet 5.5 $0.00018 $0.00292
Haiku 4.5 $0.00009 $0.00146

Measured yesterday against content hash 8b14b9b73eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deft-directive-spec-reconstruct 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.

content/skills/deft-directive-spec-reconstruct/SKILL.md · 105 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. yesterday First seen · 105 lines · 91 tokens per session scan A 8b14b9b73eef

Subscribe to this mod's changes

deft-directive-spec-reconstruct is a skill published in the GitHub repository deftai/directive (32 stars, last pushed yesterday), with no licence file. It adds 91 tokens to every session and 1,460 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-15.

Related

deft-directive-spec-reconstruct compared with skills from other repositories

deft-directive-spec-reconstruct next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deft-directive-spec-reconstructdeftai/directiveSkill32yesterdaynoneA91Claude Code, Codex
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80k9d agoMITA200Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex