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 commands/marcmallet/specforge/jiragit clone --depth 1 https://github.com/marcmallet/specforgeWhat 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 | $0.00017 | $0.00482 |
| Opus 5 | $0.00009 | $0.00241 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
jira 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
You are fetching a Jira ticket and preparing its details for spec creation.
The ticket number is: $ARGUMENTS
Step 1 — Detect which MCP server is available
Check in this order:
- Is
mcp__atlassian__getJiraIssueavailable? → use the official Atlassian Rovo MCP server - Is
mcp__mcp-atlassian__jira_get_issueavailable? → use the community mcp-atlassian server - Neither available → stop and tell the user:
- Jira integration requires an MCP server to be configured
- See the README under Jira Integration for setup instructions for both options
- Once configured, restart Claude Code and run this command again
Step 2 — Fetch the ticket
Call the available tool with the issue key $ARGUMENTS:
- Official server:
mcp__atlassian__getJiraIssuewith issueIdOrKey set to the ticket number - Community server:
mcp__mcp-atlassian__jira_get_issuewith issue_key set to the ticket number
If the call returns an error (ticket not found, not authenticated, etc.), stop and show the error clearly. Do not proceed.
Step 3 — Parse the ticket
From the response, extract:
- Title — the issue summary
- Description — the full issue description, including any acceptance criteria
Show the user a clear summary of what you found and ask:
- "Does this look right? Shall I create the spec from this?"
- Only proceed after confirmation
Step 4 — Suggest next step
Once confirmed, show the user the ready-to-run command:
"Ready to create the spec? Run:"
/specforge:create $ARGUMENTS | <title> | <description>
Where <title> and <description> are filled in with the values extracted from the ticket.
Do not create the spec file yourself. Do not invoke /specforge:create directly.
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 · 51 lines · 17 tokens per session scan A 4909122ae894
jira is a command published in the GitHub repository marcmallet/specforge (9 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 482 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.