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.
git clone --depth 1 https://github.com/AppliedIR/sift-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/commands/appliedir/sift-mcp/case)<a href="https://agentmods.dev/commands/appliedir/sift-mcp/case"><img src="https://agentmods.dev/badge/commands/appliedir/sift-mcp/case/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/commands/appliedir/sift-mcp/case"><img src="https://agentmods.dev/badge/commands/appliedir/sift-mcp/case.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 | $0.00006 | $0.00629 |
| Opus 5.5 | $0.00002 | $0.00252 |
| Sonnet 5.5 | $0.00001 | $0.00126 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
case 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Management
Run case-manager.sh for all case operations. Do not create directories,
write state files, or edit CASE.yaml directly. The script handles all
file operations deterministically.
Script location: ~/.vhir/bin/case-manager.sh
Action: $action Case name: $name
Routing
No action (just /case)
- Run:
bash ~/.vhir/bin/case-manager.sh status - If output says "No active case" → also run
listand suggest/case init <name>or/case open <name> - Otherwise, tell the user the case status from the output
init [name]
- If no name provided, ask the user for one
- Ask for a brief description (one line). If user declines, omit it.
- Run:
bash ~/.vhir/bin/case-manager.sh init <name> --description "<desc>"(omit--descriptionif none provided) - Tell the user the case was created and show the paths from the output
- Remind: evidence goes in evidence/, tool output in extractions/, documentation in reports/
open <name>
- Run:
bash ~/.vhir/bin/case-manager.sh open <name> - If the script says the case is closed, tell the user and ask if they
want to reopen it. If yes, run with
--reopen:bash ~/.vhir/bin/case-manager.sh open <name> --reopen - Tell the user the case is active and summarize the paths
- Remind: READ from evidence, WRITE to extractions, UPDATE reports
status
- Run:
bash ~/.vhir/bin/case-manager.sh status - Present the case information from the output
list
- Run:
bash ~/.vhir/bin/case-manager.sh list - Present the case list from the output
close [name]
- If no name, run:
bash ~/.vhir/bin/case-manager.sh close - If name given, run:
bash ~/.vhir/bin/case-manager.sh close <name> - Confirm closure to the user
Important
- NEVER write to
~/.vhir/active_casedirectly. The script does this. - NEVER create case directories directly. The script does this.
- NEVER edit CASE.yaml directly. The script does this.
- If the script returns an error (exit 1), show the error message to the user.
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 First seen · 74 lines · 6 tokens per session scan A 6216c6904d64
case is a command published in the GitHub repository AppliedIR/sift-mcp (18 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 629 once invoked, about $0.0000 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 2026-08-30.
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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.