Borrowing it
Nothing to install: this file belongs to vikrantd/TLDRGraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vikrantd/TLDRGraph/main/AGENTS.mdgit clone --depth 1 https://github.com/vikrantd/TLDRGraphWrote 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/instructions/vikrantd/tldrgraph/agents-md)<a href="https://agentmods.dev/instructions/vikrantd/tldrgraph/agents-md"><img src="https://agentmods.dev/badge/instructions/vikrantd/tldrgraph/agents-md/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/instructions/vikrantd/tldrgraph/agents-md"><img src="https://agentmods.dev/badge/instructions/vikrantd/tldrgraph/agents-md.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 | $0.00352 | $0.00352 |
| Opus 5.5 | $0.00141 | $0.00141 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
TLDRGraph AGENTS.md 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 1mo 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
TLDRGraph
TLDRGraph builds a source-backed feature and workflow catalog for this repository. It does not build an architecture graph, infer workflows heuristically, or run AI itself.
Run tldrgraph init to create a catalog. Run tldrgraph refresh when an
existing catalog needs updating after source changes. If either command returns
needs_feature_workflows, identify feature outcomes and immediately write the .tldrgraph/features.yaml v4 catalog index
with the reported source_hash. Then spawn one fresh source-reading subagent
for each indexed feature. Each worker writes only its assigned complete
.tldrgraph/workflows/<feature_id>.yaml v4 file; it never edits features.yaml
or another feature's workflow. Run the same command again to validate the direct
artifacts and generate the explorer.
Every capability and workflow step must cite a verified repository-relative
file, symbol, and line range. Define capabilities as user, admin, developer, or
operator outcomes. Use generated only for a proven end-to-end journey,
partial with missing_coverage for a proven fragment, and pending with no
steps when no reliable sequence can be established.
Model each feature as a directly renderable flowchart: initiating action,
proven process steps, decision branches, joined continuation, and final result.
When a workflow step has mutually exclusive paths, modes, or choices, make the
step the decision node and represent each labeled, evidence-backed branch as a
step options entry that rejoins the following proven step.
The full schema is in .tldrgraph/AGENT_CONTRACT.md.
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.
- 1mo ago Changed · -35 lines · -482 tokens per session ca10bb307776
- 1mo ago Changed · +19 tokens per session 8451ea4ca65a
- 1mo ago Changed · +22 lines · +279 tokens per session 5ba5f604e1da
- 2mo ago First seen · 43 lines · 536 tokens per session scan A 847abedbb3fb
TLDRGraph AGENTS.md is an instructions file published in the GitHub repository vikrantd/TLDRGraph (7 stars, last pushed 1mo ago), licensed MIT. It adds 352 tokens to every session, about $0.0014 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 2026-08-31.
TLDRGraph AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| TLDRGraph AGENTS.mdvikrantd/TLDRGraph | Instructions file | 7 | 1mo ago | MIT | A | 352 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |