Borrowing it
Nothing to install: this file belongs to sebastienrousseau/reconcile-mcp. 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/sebastienrousseau/reconcile-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/sebastienrousseau/reconcile-mcpWrote 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/sebastienrousseau/reconcile-mcp/agents-md)<a href="https://agentmods.dev/instructions/sebastienrousseau/reconcile-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sebastienrousseau/reconcile-mcp/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/sebastienrousseau/reconcile-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sebastienrousseau/reconcile-mcp/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 | $0.00713 | $0.00713 |
| Opus 5.5 | $0.00285 | $0.00285 |
| Sonnet 5.5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade B, and why
reconcile-mcp AGENTS.md scanned grade B with 1 finding 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 15d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
2. Ensure linter and formatter pass without warnings or new suppressions. This is a copy
84% identical to bankstatementparser-mcp AGENTS.md — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Invariants for AI-assisted contributions to reconcile-mcp. Read this before changing anything.
Everything here applies equally to humans and automated agents. It is addressed to agents because agents can make breaking changes across multiple files before anyone notices.
1. Core Invariants
- Strict SemVer sequencing policy: Public releases stay on the
0.0.xline and increment strictly by0.0.1. Never manually edit version numbers outside the active release branchfeat/v<next-version>.v0.1.0is forbidden untilv0.0.999exists. - Single Active Release PR Invariant: Across all repositories, there MUST be at most ONE active pull request targeting
main, which MUST be the release iteration branchfeat/v<next-version>. - Dual licensing: The repository is dual-licensed under Apache-2.0 OR MIT. All files must declare an SPDX license header.
- Single source of truth: The version in
pyproject.tomlis the single source of truth. It must agree with__version__,glama.json,server.json,CITATION.cff, andCHANGELOG.md(verified byscripts/verify_versions.py). - Deterministic explainable matching: All core reconciliation tools (
reconcile,explain_match,normalize_pain001,normalize_camt053,list_sandbox_scenarios,load_sandbox_scenario,run_sandbox_scenario,match_names_probabilistic,match_amounts_with_fx_drift,reconcile_many_to_many) must remain side-effect-free, read-only, and idempotent.
2. Before You Claim To Be Done (Verification Gates)
Before concluding any task or preparing a commit, run:
make check
Or run the individual gates:
pytest --cov=reconcile_mcp --cov-branch --cov-report=term-missing --cov-fail-under=100
ruff check .
black --check .
mypy reconcile_mcp
python3 scripts/verify_versions.py
All unit tests and conformance tests must pass with 0 failures, 0 warnings, and 100% line and branch coverage.
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.
- 15d ago First seen · 49 lines · 713 tokens per session scan B 3c9829b5e83d
reconcile-mcp AGENTS.md is an instructions file published in the GitHub repository sebastienrousseau/reconcile-mcp (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 713 tokens to every session, about $0.0029 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). It is 84% identical to bankstatementparser-mcp AGENTS.md, differing in 15 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.