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 instructions/dvryaboy/dblect/claude-mdgit clone --depth 1 https://github.com/dvryaboy/dblectWrote 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/dvryaboy/dblect/claude-md)<a href="https://agentmods.dev/instructions/dvryaboy/dblect/claude-md"><img src="https://agentmods.dev/badge/instructions/dvryaboy/dblect/claude-md.svg" alt="Measured on agentmods" 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 | $0.00876 | $0.00876 |
| Opus 5 | $0.00438 | $0.00438 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
dblect CLAUDE.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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Style
We avoid stringy typing like the plague. We use rigorous types.
We reach for an existing helper before writing a parallel one, and generalize it when a second caller needs a variant. A comment or commit message that reaches for "mirroring", "duplicate of", or "acceptable for now" is a signal to stop and reuse the original instead.
Testing
We test rigorously. Whenever applicable, we design quality PBT tests, or otherwise leverage provers and exhaustive testing. We do not write tests for tests' sakes. We avoid test theater. We prefer to test at the boundaries instead of implementation specifics; tests should survive implementation changes that do not change contracts. Excessive use of mocking is a smell. Loads of boilerplate is a smell. Pin contracts, not coincidences. If fragile cooperation is observed (two functions work correctly together only because of implementation details, not contract guarantees), fix the contracts in code rather than pinning the accidental behavior in a test.
We work test-first: the failing test (or the property / lattice-law spec) comes before the implementation, so it pins the intended contract rather than rationalizing whatever the code happens to do. When the contract is amenable, we design the property-based test and its generators first, before the code, so the generator is not shaped to fit the implementation.
A whole suite passing on its first run is a smell rather than a win: it usually means the tests are weak or were written after the code. When it happens, we prove the tests bite by injecting deliberate contract violations and confirming a test fails for each.
We enumerate the input space rather than sampling it: a condition over a closed type earns a test per value, and the common ones (COUNT(*) among the duplicate-sensitive aggregates) belong in that space rather than being deferred as edge cases.
Soundness
We discharge each predicate or guard to an exact decision procedure before coding it, with a counterexample that marks its edge and a test that pins it. A plausible structural proxy standing in for a precise semantic condition is where the subtle bugs live.
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.
- 3d ago First seen · 47 lines · 876 tokens per session scan A d65339e34ce0
dblect CLAUDE.md is an instructions file published in the GitHub repository dvryaboy/dblect (21 stars, last pushed 4d ago), licensed Apache-2.0. It adds 876 tokens to every session, about $0.0044 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 2026-08-30.
Other instructions, from other repositories
vscode_abap_remote_fs CLAUDE.md
Instructions for marcellourbani/vscode_abap_remote_fs, covering abap fs development guidelines, workflow and constraints.
sheal AGENTS.md
Instructions for liwala/sheal, covering agent instructions, agent operating policy, 1. tdd discipline — strict order, the only exception: spikes and 2. tests assert intent.
spec-driven-tdd AGENTS.md
Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.
mcp-repo-onboarding AGENTS.md
Instructions for rogermt/mcp-repo-onboarding, covering agents.md — agent & copilot instructions, current status, output verification, project identity and ⚠️ critical: tdd required.
arxiv-agent-mcp AGENTS.md
AGENTS.md instructions for tbaraniuk/arxiv-agent-mcp, covering agents.md, roles, test-writer, implementer and per-task loop.
pythorust_tg copilot-instructions.md
Copilot instructions for stden/pythorust_tg, covering github copilot instructions, project, tdd workflow, test format and rust.