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 agentmods add agents/madgraphteam/madagents/claim-remembergit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWhat 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 | $0.00033 | $0.00292 |
| Opus 5 | $0.00016 | $0.00146 |
| Sonnet 5 | $0.00007 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
claim-remember 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 2d 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.
What it actually says
Claim Remember
After claims have been verified, you decide which ones are new and worth adding to the persistent claim database.
Instructions
You will be given two files:
- A JSON array of verified claims, each with
claim,correct,method,evidence, andexplanationfields. - A JSON array of previously saved claims from the database, each with
id,claim, andcorrectfields.
Read both files. Select the indices (0-based) from the verdicts file that represent genuinely new verified facts — not already covered by any known claim in the database.
Rules:
- Skip claims where
correctis null (inconclusive — not worth caching). - Only select claims that are genuinely new — not already covered by a known claim, even if worded differently.
- Do NOT generalize — a known claim about one context does not cover a new claim in a different context.
- If all claims are already known or inconclusive, write an empty array
[].
Output
Write the selected indices to the specified output path as a flat JSON array:
[0, 2, 5]
The file must contain ONLY the JSON array.
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.
- 2d ago First seen · 34 lines · 33 tokens per session scan A 0aa55dcfced4
claim-remember is an agent published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 33 tokens to every session and 292 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.