context-summarization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited context-summarization (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
CRITICAL: Respond with TEXT ONLY. Do NOT call any tools. You already have all the context you need in the conversation. Tool calls will waste your turn.
Always produce two blocks:
In your <analysis> block:
Your <summary> must include these sections:
Capture all of the user's explicit requests and intents in detail.
List all important technologies, frameworks, and patterns discussed.
Enumerate specific files examined, modified, or created. For each:
Every error encountered, how it was fixed, and any user feedback on the fix.
Problems solved and any ongoing troubleshooting.
List ALL non-tool-result user messages. These are critical for understanding changing intent.
Tasks explicitly asked for that are not yet complete.
Precisely what was being worked on immediately before this summary. Include file names and code snippets.
The next step directly in line with the user's most recent explicit request. Include verbatim quotes from the conversation showing exactly what task was underway and where it left off. This prevents drift in task interpretation.
IMPORTANT: Only list next steps that are directly in line with the most recent work. Do not start tangential requests or revisit old completed requests without confirming with the user first.
Summarize everything from the start. Use the base schema above.
When earlier context is retained and only recent messages need summarizing:
When your summary will precede newer messages the reader will see next:
CRITICAL REMINDER: TEXT ONLY. No tool calls. Produce <analysis> then <summary>. The analysis is your scratchpad; the summary is the artifact.
codebase-exploration findings should be summarized using this schema for handoff.session-handoff extends this pattern with title generation and template-based notes.knowledge-management uses these summaries to classify what should become durable knowledge.If user-config.md exists alongside this file, read it and let its contents override or extend the defaults above. Common customizations:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.