descend

descend is a skill for Claude Code, Codex from Kshitijpalsinghtomar/depth-skills. It costs 21 tokens per session (1,779 once invoked), scanned A, original, MIT.

A reasoning aid that checks whether a familiar solution pattern really fits the problem, then rebuilds the reasoning from basic facts when it does not.

In plain words
What is it for?
Use it before applying known designs, fixes, or analogies to an unfamiliar coding problem.
Why use it?
It helps prevent surface similarities from leading to solutions that work for a different kind of problem.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before applying known designs, fixes, or analogies to an unfamiliar coding problem.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kshitijpalsinghtomar/depth-skills/ds-descend
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 Kshitijpalsinghtomar/depth-skills --skill ds-descend
Clone the repo
git clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skills

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 descend

README.md
[![agentmods](https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-descend/github.svg)](https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-descend)
Your own site
<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-descend"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-descend/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 descend

Your own site · 80×15
<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-descend"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-descend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,779 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 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 5.1 $0.00021 $0.01779
Opus 5 $0.00010 $0.00890
Sonnet 5 $0.00004 $0.00356
Haiku 4.5 $0.00002 $0.00178

Measured 11d ago against content hash 1889211f4b44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

descend 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 11d 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/ds-descend/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DESCEND — Pattern Audit & First-Principles Derivation

Every answer you generate is built from patterns — compressed experience retrieved from training: "In situations like X, do Y." This is efficient when the match is real.

It is catastrophic when it isn't. And you do not check.

Pattern gravity matches on surface similarity — keywords, domain, structure — without verifying whether the underlying problem has the same internal structure as the one the pattern was designed for. Problems that look alike on the surface can have completely different mechanics underneath. The pattern that solved one will silently damage the other.

This skill has two phases:

  • Phase 1: AUDIT — is the pattern match real, or is it a surface-level false analogy?
  • Phase 2: DERIVE — if the match is false, reason from fundamental truths upward.

Phase 1: Pattern Audit

Step 1 — MAKE THE PATTERN VISIBLE

Write down the pattern you are about to apply. Often you apply patterns unconsciously — the solution appears without explicit acknowledgment of its source.

PATTERN IDENTIFICATION
────────────────────────────────────────
Pattern I'm applying:  [name or description of the template/approach]
Source domain:         [what type of problem this pattern was designed for]
Surface trigger:       [what about THIS problem triggered this pattern match]
Conscious or auto:     [did I deliberately choose this, or did it appear unbidden?]
────────────────────────────────────────

If you cannot name the source pattern, you are operating on unconscious analogy — the most dangerous mode, because the match was never evaluated.

Artifact: The pattern identification card. Phase 1, Step 2 uses this directly.

Step 2 — CHECK STRUCTURAL PRECONDITIONS

Every solution pattern has preconditions — things that must be true for it to work. List the preconditions of the pattern you identified, then check each against THIS problem:

PRECONDITION CHECK
────────────────────────────────────────
P1: [pattern requires X]
    This problem: [X is true / false / uncertain]
    Match: [confirmed / broken / uncertain]

P2: [pattern requires Y]
    This problem: [Y is true / false / uncertain]
    Match: [confirmed / broken / uncertain]

P3: [pattern requires Z]
    This problem: [Z is true / false / uncertain]
    Match: [confirmed / broken / uncertain]
────────────────────────────────────────

Read the full file on GitHub · 202 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. 11d ago First seen · 202 lines · 21 tokens per session scan A 1889211f4b44

Subscribe to this mod's changes

descend is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,779 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.