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 skills add trilwu/secskills --skill maintaining-engagement-stategit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/skills/trilwu/secskills/maintaining-engagement-state)<a href="https://agentmods.dev/skills/trilwu/secskills/maintaining-engagement-state"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/maintaining-engagement-state/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/skills/trilwu/secskills/maintaining-engagement-state"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/maintaining-engagement-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 158 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00100 | $0.02585 |
| Opus 5 | $0.00050 | $0.01293 |
| Sonnet 5 | $0.00020 | $0.00517 |
| Haiku 4.5 | $0.00010 | $0.00259 |
Grade A, and why
maintaining-engagement-state 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- maintaining-engagement-state — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining Engagement State
An engagement lasts weeks. A session does not. The gap between those two facts is where work gets repeated, findings lose their evidence, credentials become unattributable, and artifacts get left on production because nobody wrote down that they were placed.
This is not administrative overhead bolted onto the real work. Provenance is what makes a finding reportable, and the artifact register is what makes cleanup possible. Neither can be reconstructed afterwards from terminal scrollback.
Assume everything not written to the record is lost: not merely forgotten, but silently lost, so the next session confidently redoes it or contradicts it.
When to Use
- Any engagement or investigation continuing past a single sitting
- Resuming after a break, or picking up someone else's work
- Approaching a context boundary with unrecorded state
- Handing off between analysts, shifts, or teams
- Before running anything that writes to a target
- When you cannot answer "which host did this credential come from?"
When NOT to Use
- Writing the client-facing deliverable — use
reporting-security-findings; this skill produces the raw material that skill consumes - Deciding whether a finding is real — that is the relevant testing or analysis skill; record the outcome here either way
- Chain of custody for evidence that may reach court — legal custody has
formal requirements beyond this; use
responding-to-incidentsand follow the organisation's counsel - A single self-contained task finished in one sitting with nothing left on target
The Six Records
Keep these in one file, in the repository or case folder, updated as you go — not reconstructed at the end.
1. Scope and authorization
In-scope targets and explicit exclusions, the testing window, the named contact, and where the authorization letter lives. Copy the exclusions verbatim; paraphrasing scope is how people test the wrong estate.
Record one more field, because "in scope" and "reachable" are different questions. Egress mode says what this engagement is allowed to talk to:
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.
- 11d ago First seen · 232 lines · 100 tokens per session scan A 30cde0fdd64b
maintaining-engagement-state is a skill published in the GitHub repository trilwu/secskills (138 stars, last pushed 6d ago), licensed MIT. It adds 100 tokens to every session and 2,585 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…