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 Sagargupta16/claude-skills --skill starter-session-auditgit clone --depth 1 https://github.com/Sagargupta16/claude-skillsWrote 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/sagargupta16/claude-skills/starter-session-audit)<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/starter-session-audit"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/starter-session-audit/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/sagargupta16/claude-skills/starter-session-audit"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/starter-session-audit.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 | $0.00073 | $0.01389 |
| Opus 5 | $0.00036 | $0.00694 |
| Sonnet 5 | $0.00015 | $0.00278 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
starter-session-audit 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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
starter-session-audit
A lightweight end-of-session audit. Catches things the user said during the session that should be saved permanently so they never have to say them again.
What this skill does
Two things, and only two things:
- Scans the conversation for uncaptured learnings -- corrections, preferences, decisions, and new context that are not already in the project's instruction files.
- Proposes where to save each finding -- which file, which section, exact wording. The user approves or skips each one.
No file reorganization. No cleanup. No progress tracking. Just: "Did I learn anything this session that should be remembered?"
Step 1: Discover the persistence layout
Claude Code sessions can use several layers of persistence. Load whichever files exist:
- Project CLAUDE.md -- at repo root or workspace root (standing instructions for this project).
- User-global CLAUDE.md -- typically
~/.claude/CLAUDE.md(preferences that apply everywhere). - Memory / MEMORY.md -- any workspace-level memory index file plus any topical files it points at.
- Live-state files -- STATUS.md, TODO.md, or similar workspace files if the project uses them.
- Local-only override --
CLAUDE.local.md(git-ignored, machine-specific). - Rules --
.claude/rules/*.mdif the project uses path-scoped rule files. - Resources --
.claude/resources/*.mdif the project keeps task-triggered reference docs. - Repo-level CLAUDE.md files in any repo touched during the session.
If the project only has a single CLAUDE.md, that's fine. The audit adapts.
Step 2: Scan the conversation
Walk the full conversation top to bottom. Look for four signal types.
A. Corrections
The user fixed something Claude produced -- changed wording, rejected an approach, said "no, do it this way instead." Each correction reveals an underlying rule.
Ask: what preference or rule drove this change?
Example: User changed "refactor the whole module" to "just the one function". Rule: "Prefer surgical changes; don't expand scope without asking."
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.
- 5d ago First seen · 128 lines · 73 tokens per session scan A 3565b228c0a0
starter-session-audit is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 1,389 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
doctor
Use to health-check the user's haku memory directory — validate file layout, catch problems before they cost data. Triggers: "run haku doctor", "check my reflection files", "is my data okay", "back up my reflections", "I'm moving to a new machine". Validates /haku-work-reflections/ (or $HAKUWORKREFLECTIONSHOME)…
capture
Use to log something from the current conversation into the user's haku memory — a decision just made, a win that surfaced, a stakeholder observation, a self-insight. Triggers: "log this", "capture this", "save that decision", "remember this", or a substantive conversation just concluded. Distinct from decision-log /…
kanban-dev-lane
Use when a Hermes Kanban worker wants to run an autonomous implementation delegation lane with a 3-tier fallback chain across claudy -> codex (--yolo) -> agyd (agy --dangerously-skip-permissions) -> Hermes direct on quota exhaustion.
release
This skill should be used when the user wants to create a new release — bump version, tag, push, create GitHub release, and optionally publish to npm. Use when user says "release", "bump version", "publish", "cut a release", or "release candidate".
council
4-voice parallel deliberation for architecture, tech selection, or design decisions with no clear answer. Each voice gets independent context to prevent anchoring bias. Use when the user says "council", "deliberate", "second opinion", or faces a trade-off between multiple valid approaches.
orbit
Autonomous pipeline — spec requirements, execute implementation, audit quality, and ship. Runs the full epic-harness orbit cycle in one go. Use when the user says "orbit", "full pipeline", "spec to ship", or describes a feature that needs end-to-end handling.