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.
npx skills add Kshitijpalsinghtomar/depth-skills --skill ds-anchorgit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skillsWrote 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.
[](https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-anchor)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-anchor"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-anchor/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.
<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-anchor"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-anchor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.01149 |
| Opus 5 | $0.00010 | $0.00575 |
| Sonnet 5 | $0.00004 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
anchor 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ANCHOR — Objective Drift Detector
You have been working on this for a while. You've gone deep. You've explored branches, found interesting subproblems, and pursued them.
Stop. Write down what the user originally asked for. Now write down what you are currently doing.
Are they the same thing?
The Failure Mode You Must Recognize
You are doing something that feels important, useful, and intellectually engaging — that was not requested. Common drift patterns:
- Means-ends inversion: User asked for a feature. You're now optimizing the database schema — a means, not the end. The schema became interesting. The feature is forgotten.
- Scope creep: User asked for one thing. You noticed five related things and are building six.
- Tangent following: Edge case → design question → architecture → technology comparison. You're comparing technologies. User asked about an edge case.
- Complexity attraction: Simple solution exists. You're building the complex one because it's more engaging.
- Solution-first drift: You started with a technology you like and are reshaping the problem to justify it.
These feel productive. They are not productive toward the objective.
The Protocol
Step 1 — SET THE ANCHOR (at task start)
At the beginning of any extended task, write:
ANCHOR
────────────────────────────────────────
User's exact words: [their literal request — quoted]
My interpretation: [what I believe they need — may differ]
Success looks like: [specific deliverable that satisfies this]
────────────────────────────────────────
This anchor does not move unless the user explicitly moves it.
Artifact: The anchor. Step 2 checks against this periodically.
Step 2 — THE DRIFT CHECK (run periodically)
At any point during extended work, write:
DRIFT CHECK
────────────────────────────────────────
Original objective: [from the anchor — Step 1]
What I'm doing NOW: [be honest — what are you actually working on right now?]
Connection chain:
[current activity] → serves → [intermediate goal] → serves → [original objective]
Chain length: [number of links]
Drift status: [on target / minor drift / significant drift / lost]
────────────────────────────────────────
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.
- 11d ago First seen · 143 lines · 21 tokens per session scan A 076d1f300200
anchor 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 1,149 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.
Other skills, from other repositories
scope-lock
Use when you want to lock the session to a specific scope description, injecting it into purpose-gate context and optionally blocking out-of-scope tool calls.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
vox-video-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end with Aliyun Bailian CLI + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
api-database-mongodb
Native MongoDB driver (the mongodb npm package) - MongoClient lifecycle, typed collections, CRUD result shapes, cursors, aggregation pipelines, index design, transactions.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.