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 skills/servosity/msp-skills/abnormalnpx skills add Servosity/msp-skills --skill abnormalgit clone --depth 1 https://github.com/Servosity/msp-skillsWhat 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 | $0.00090 | $0.04746 |
| Opus 5 | $0.00045 | $0.02373 |
| Sonnet 5 | $0.00018 | $0.00949 |
| Haiku 4.5 | $0.00009 | $0.00475 |
Grade A, and why
abnormal 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 610 B
- AGENTS.md 2.3 KB
- CHANGELOG.md 3.1 KB
- cli/.golangci.yml 147 B
- cli/cmd/abnormal-cli/main.go 353 B
- cli/cmd/abnormal-mcp/main.go 2.1 KB
- cli/go.mod 966 B
- cli/go.sum 7.0 KB
- cli/internal/cache/cache.go 1.7 KB
- cli/internal/cli/abusecampaigns_retrieve-2.go 3.2 KB
- cli/internal/cli/abusecampaigns_retrieve.go 6.2 KB
- cli/internal/cli/abusecampaigns.go 676 B
- cli/internal/cli/agent_context.go 6.8 KB
- cli/internal/cli/aggregations_attack-frequency-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_attack-stopped-retrieve.go 3.9 KB
- cli/internal/cli/aggregations_attack-strategy-breakdown-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_attack-vector-breakdown-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_attacker-origin-retrieve.go 3.9 KB
- cli/internal/cli/aggregations_dashboard-summary-retrieve.go 3.9 KB
- cli/internal/cli/aggregations_most-impersonated-employee-non-vip-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_most-impersonated-employee-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_most-impersonated-employee-vip-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_most-impersonated-vendor-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_recipient-employees-non-vip-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_recipient-employees-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_recipient-employees-vip-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_sender-impersonation-breakdown-retrieve.go 4.0 KB
- cli/internal/cli/aggregations_trending-attacks-retrieve.go 3.9 KB
- cli/internal/cli/aggregations.go 1.6 KB
- cli/internal/cli/analytics.go 5.0 KB
- cli/internal/cli/api_discovery.go 3.6 KB
- cli/internal/cli/api_resources_resources-actions-create.go 8.0 KB
- cli/internal/cli/api_resources_resources-create-create.go 8.0 KB
- cli/internal/cli/api_resources_resources-retrieve-2.go 3.2 KB
- cli/internal/cli/api_resources_resources-retrieve.go 3.6 KB
- cli/internal/cli/api_resources_resources-update-partial-update.go 7.6 KB
- cli/internal/cli/api_resources.go 888 B
- cli/internal/cli/auth.go 6.5 KB
- cli/internal/cli/cases_actions_cases-retrieve.go 3.4 KB
- cli/internal/cli/cases_actions.go 580 B
- cli/internal/cli/cases_analysis_cases-retrieve.go 3.2 KB
- cli/internal/cli/cases_analysis.go 584 B
- cli/internal/cli/cases_create.go 7.8 KB
- cli/internal/cli/cases_retrieve-2.go 3.1 KB
- cli/internal/cli/cases_retrieve.go 3.7 KB
- cli/internal/cli/cases.go 762 B
- cli/internal/cli/channel_workflow.go 5.4 KB
- cli/internal/cli/data_source.go 22 KB
- cli/internal/cli/deliver.go 3.5 KB
- cli/internal/cli/detection360_reports-create.go 7.7 KB
- cli/internal/cli/detection360_reports-retrieve.go 5.0 KB
- cli/internal/cli/detection360.go 670 B
- cli/internal/cli/doctor_verdict.go 12 KB
- cli/internal/cli/doctor.go 21 KB
- cli/internal/cli/email_search_search-activities-retrieve.go 4.0 KB
- cli/internal/cli/email_search_search-activities-status-retrieve.go 3.3 KB
- cli/internal/cli/email_search_search-create.go 13 KB
- cli/internal/cli/email_search_search-messages-attachments-download-retrieve.go 4.4 KB
- cli/internal/cli/email_search_search-messages-eml-retrieve.go 2.4 KB
- cli/internal/cli/email_search_search-remediate-create.go 9.6 KB
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 · 392 lines · 90 tokens per session scan A 08d9fa7571f6
abnormal is a skill published in the GitHub repository Servosity/msp-skills (33 stars, last pushed 7d ago), with no licence file. It adds 90 tokens to every session and 4,746 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
prove-a-scanner-fires
Pair every source-scanning hygiene test with a proof that it detects a planted violation, that its walk actually opened files, and that it is no laxer than the tool it mirrors. Use when writing or reviewing any test that greps a crate's own text — citation audits, hardcoded-constant checks, imputation scans…
add-module
Add a new crate to the bioprism workspace implementing a blueprint section, including registering it, choosing dependencies without creating cycles, and the honesty conventions every crate must follow. Use when starting a new module, when asked to cover an uncovered blueprint section, or when setting up work for a…
check-parity
Verify the CPython reference, the eager Rust path and the indexed store still agree byte for byte on a Context Certificate digest. Use after touching canonical serialization, hashing, compiler passes, the store, or any serde configuration, and before any release or wire-format change.
verify-crate
Verify a bioprism crate is genuinely green — tests passing and clippy at zero warnings — and recognise the environment failures that masquerade as test failures. Use before claiming a crate is done, after landing an agent's work, when a test count looks wrong or lower than expected, or when cargo test reports a…
mission-lifecycle
Author, preflight, and execute aurora-agent missions — validated DAGs of MCP tool calls. Use when asked to build or run a mission, when a mission is refused with invalidmission or operationsgateacceptancerequired, when deciding between synchronous agentmission and async submission, or when wiring evaluator reviews and…
virtualsms-sms-verification
Real SIM-card SMS verification for AI agents via VirtualSMS MCP server. TRIGGERS: SMS verification, OTP code, phone number, virtual number, SIM card, two-factor authentication, account verification, WhatsApp verify, Telegram verify, real SIM, agent phone, MCP SMS, virtualsms. Use when an agent needs to receive an SMS…