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/WYRE-AI/msp-claude-pluginsWrote 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/wyre-ai/msp-claude-plugins/evidence-pack)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/evidence-pack"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/evidence-pack.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 | $0.00015 | $0.01038 |
| Opus 5 | $0.00008 | $0.00519 |
| Sonnet 5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
evidence-pack 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Pack
Build a structured, source-cited compliance evidence package for a client, mapping live tenant configuration and documentation to the controls of a named framework.
Prerequisites
- Conduit MCP Gateway connected (
conduit) - At least one compliance-relevant connector available for the client (CIPP for M365/Entra evidence is the strongest single connector; Liongard and IT Glue/Hudu add infrastructure and documentation evidence)
- Client identifiable by name in the connected PSA/tenant list
Steps
- Discover available tools. Call
conduit__search_toolsto find every compliance-relevant tool connected for this org — do not assume CIPP, Liongard, and IT Glue are all present. Record which vendor families are available and which are not. - Resolve the client. Confirm the target client against connected systems (e.g.
cipp__list_tenantsfor the M365 tenant,itglue__search_organizationsfor the documentation org record) before pulling anything client-scoped. - Resolve the framework to a control list. Use the framework named in
framework(cis,soc2,hipaa) to select the relevant control families; ifframeworkis omitted, use the general representative control set from theevidence-mappingskill. - Invoke the
evidence-packageragent with the resolved client and framework. The agent maps each control to its evidence source per theevidence-mappingskill, queries every connected vendor family, and classifies each finding as Configured, Documented, Contradicted, or Unable to Verify. - Present the package, leading with Contradicted and Unable to Verify findings, followed by the full control-by-control evidence table.
Arguments
| Argument | Required | Default | Description |
|---|---|---|---|
client |
Yes | — | The client/organization name to build the evidence package for |
framework |
No | general |
Target framework: cis, soc2, hipaa, or general for a representative cross-framework control set |
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 · 115 lines · 15 tokens per session scan A 6c4c22d943e7
evidence-pack is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,038 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 2026-09-04.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.