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 mlopscommunity/Coding-Agents-Conference-skills --skill objective-researchgit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-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/mlopscommunity/coding-agents-conference-skills/objective-research)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/objective-research"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/objective-research/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/mlopscommunity/coding-agents-conference-skills/objective-research"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/objective-research.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 | $0.00043 | $0.01931 |
| Opus 5.5 | $0.00017 | $0.00772 |
| Sonnet 5.5 | $0.00009 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
objective-research 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 2mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective Research via Context Separation
Overview
A two-context technique for producing unbiased codebase research. The first context (intent context) knows what you are building and decomposes the ticket into targeted research questions. The second context (research context) receives only those questions — never the ticket — and returns compressed factual findings about how the code works today.
Core principle: If the research agent knows what you are building, it injects opinions into facts. Confirmation bias causes it to emphasize code paths that support the anticipated solution and downplay alternatives. Separate intent from investigation.
When to Use
- Before starting implementation on a ticket that touches unfamiliar code
- When you need to understand how an existing feature works end-to-end
- When tracing data flow, call paths, or schema shapes across multiple files
- Any time research quality matters more than speed
When NOT to Use
- Trivial changes where you already understand the code
- Pure greenfield work with no existing code to investigate
- Quick lookups (e.g., "what version of React is installed")
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Giving the research agent the full ticket | It will shape findings to match the anticipated solution. You get confirmation, not truth. |
| Asking broad, open-ended research questions | "How does auth work?" produces a rambling survey. Targeted questions like "What function validates JWT expiry and what does it return on failure?" produce usable facts. |
| Mixing factual questions with design questions | "What's the best way to add caching here?" is a design opinion, not research. Research should describe what exists, not what should exist. |
| Skipping the question-generation step | Jumping straight into research without decomposing the ticket means you investigate reactively — following whatever catches your eye — instead of systematically covering what you need to know. |
| Reusing the same context for research and implementation | The implementation context has intent. If it also does the research, the same bias problem returns. Use a fresh context for investigation. |
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.
- 2mo ago First seen · 157 lines · 43 tokens per session scan A f9267b0eaee8
objective-research is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (39 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,931 once invoked, about $0.0002 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 2026-08-30.
objective-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| objective-researchmlopscommunity/Coding-Agents-Conference-skills | Skill | 39 | 7mo ago | Apache-2.0 | A | 43 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 5d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |