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-fidelitygit 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-fidelity)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-fidelity"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-fidelity/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-fidelity"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-fidelity.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 | $0.01281 |
| Opus 5 | $0.00010 | $0.00641 |
| Sonnet 5 | $0.00004 | $0.00256 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
fidelity 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 12d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FIDELITY — Compression Integrity Verifier
You just did deep thinking. You explored approaches, found edge cases, identified caveats, surfaced conditions. Now you're compressing it into a clean final answer.
This is the moment truth disappears.
The Failure Mode You Must Recognize
Two pressures compete: be thorough and be concise. The result is lossy compression:
- "This works IF X" becomes "This works" (condition dropped)
- "True EXCEPT when Y" becomes "True" (exception erased)
- "70% confident because Z" becomes a declarative statement (uncertainty hidden)
- "Option B was close, better if Q changes" becomes invisible (alternative forgotten)
The summary is cleaner, shorter, more confident — and less true than the analysis that produced it. The user makes decisions based on a simplified reality that you know is incomplete.
The Protocol
Step 1 — TAG: Mark Critical Information Before Compressing
Before writing the compressed version, read the full analysis and tag every item that, if dropped, makes the summary misleading. Write each tag:
CRITICAL INFORMATION TAGS
────────────────────────────────────────
TAG 1 — CONDITION:
Full: "[recommendation] IF [condition]"
If dropped: user tries it where [condition] is false → [consequence]
TAG 2 — EXCEPTION:
Full: "True EXCEPT when [scenario]"
If dropped: user applies universally → hits [scenario] unprepared
TAG 3 — UNCERTAINTY:
Full: "[confidence level] because [evidence state]"
If dropped: user treats as certain → no contingency when wrong
TAG 4 — ALTERNATIVE:
Full: "Option B was close — better if [condition changes]"
If dropped: user can't adapt when conditions change
TAG 5 — DEPENDENCY:
Full: "Depends on [X] being true/available/stable"
If dropped: user doesn't verify [X] → failure when [X] is absent
────────────────────────────────────────
Not every answer has all five types. Tag what exists. The types to scan for:
- Conditions — "works IF"
- Exceptions — "true EXCEPT"
- Uncertainties — confidence levels, evidence gaps
- Alternatives — near-winners that matter if context changes
- Dependencies — things this answer relies on
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.
- 12d ago First seen · 163 lines · 21 tokens per session scan A 42bff5dfefd4
fidelity 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 1,281 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
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.
ai-orchestration-langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.
ai-provider-cohere-sdk
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection.