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/timohaa/simple-jira-mcp/agents-mdgit clone --depth 1 https://github.com/timohaa/simple-jira-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/timohaa/simple-jira-mcp/agents-md)<a href="https://agentmods.dev/instructions/timohaa/simple-jira-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/timohaa/simple-jira-mcp/agents-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 5.1 | $0.00930 | $0.00930 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
simple-jira-mcp 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 5d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project
MCP server providing Jira Cloud integration for AI agents via stdio transport.
Built with FastMCP (Python). See API_REFERENCE.md for tool schemas, error
codes, and JQL patterns.
Critical: No stdout
NEVER write to stdout — not print(), not any library default.
Stdout is the MCP JSON-RPC transport channel. Any stray output corrupts the
protocol and breaks the server silently.
Use stderr via the logging module for all diagnostics.
Commands
./check.sh # All checks (lint + mypy + tests)
./check.sh -l # Ruff lint only
./check.sh -m # Mypy only
./check.sh -t # Tests only
./check.sh -c # Tests with coverage
./check.sh -f # Auto-fix lint
./check.sh -a # Explicitly run all checks
./check.sh -h # Show help
Run check_thresholds (scopewalker MCP tool) before committing to enforce
file <300 / function <100 line limits.
Behavior
- Minimum footprint. Write the minimum code that solves the problem — no speculative abstractions, no drive-by renames, no unrelated cleanup bundled into the same change.
- Verify, don't trust.
./check.shpassing is necessary but not sufficient — read a tool's tests to confirm its actual behavior. - Never create
_enhanced,_v2, or_newduplicate file variants — edit the original file.
Prefer LSP over Grep/Read for code navigation (workspaceSymbol,
findReferences, goToDefinition, hover). Use Grep only for text/pattern
searches.
Key Files
src/server.py— MCP entry point (FastMCP)src/config.py— Configuration loadingsrc/tools/— Tool implementations (one file per tool group)src/jira/client.py— Jira REST API v3 clientsrc/jira/adf.py— ADF ↔ plain text conversionsrc/utils/— Validation and error handling
Jira API Gotchas
These are non-obvious behaviors that cause real bugs:
- Search is POST, not GET:
POST /rest/api/3/search/jql - All queries must be bounded — always include at least one filter (project, assignee, date range, etc.). Any one filter is enough; the query need not be scoped to a project.
- Quote reserved words in JQL values —
project = "ON"works,project = ONfails, becauseONis a JQL reserved word (as areIN,IS,TO,BY,WAS,CF, …). Quoting is always safe. - Date boundaries are exclusive at midnight:
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.
- 5d ago First seen · 103 lines · 930 tokens per session scan A fe11fa2b5156
simple-jira-mcp AGENTS.md is an instructions file published in the GitHub repository timohaa/simple-jira-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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 instructions, from other repositories
RivalSearchMCP AGENTS.md
AGENTS.md instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
cpf-validador CLAUDE.md
Claude Code instructions for opastorello/cpf-validador, covering claude.md, comandos, rodar localmente (fastapi + fastmcp na porta 8000), docker (porta 8002 conforme docker-compose.yaml) and arquitetura.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
ocr-mcp AGENTS.md
AGENTS.md instructions for sandraschi/ocr-mcp, covering ocr-mcp — agent guide, entry points, quick ref, standards and key files.
calibremcp AGENTS.md
AGENTS.md instructions for sandraschi/calibremcp, covering calibremcp — agent guide, entry points, standards, key files and http daemon + stdio proxy.
sagemath-mcp CLAUDE.md
Instructions for XBP-Europe/sagemath-mcp, covering claude.md, project, commands, linting and testing.