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 voxpelli/vp-claude --skill session-reflectgit clone --depth 1 https://github.com/voxpelli/vp-claudeWrote 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/voxpelli/vp-claude/session-reflect)<a href="https://agentmods.dev/skills/voxpelli/vp-claude/session-reflect"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/session-reflect.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 | $0.00147 | $0.02397 |
| Opus 5 | $0.00073 | $0.01198 |
| Sonnet 5 | $0.00029 | $0.00479 |
| Haiku 4.5 | $0.00015 | $0.00240 |
Grade A, and why
session-reflect 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 7d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Reflect
Review the current conversation, extract insights worth persisting in Basic Memory, find the right existing notes, preview proposed captures, and write only what the user approves.
User-triggered: extracts candidates, finds the right target notes, shows a grouped preview, and waits for approval before writing. Thorough by design — exercises judgment and lets the user decide what's worth keeping.
Edge Cases
- Empty conversation / no insights — report "No durable insights found in this conversation" and exit. Do not force captures.
- BM unavailable — report the error and suggest trying again later. The PostToolUseFailure hook covers BM write-tool errors (write_note, edit_note, schema_validate, schema_diff, schema_infer); other tool failures surface raw.
- All insights already captured — if
build_context1-hop checks show every candidate is in a neighbor, report "All insights from this session appear to already be captured" with note links. - User declines all — respect the decline. Report "No observations written" and exit cleanly.
- Very long conversation — cap at 10 candidates in the preview. Note "N additional minor insights omitted — request a second pass if needed."
- Target note has no Observations section — flag to the user that the
note needs structural repair. Do not use
operation="append"withsection="Observations"(it appends to end of file, not end of section).
Workflow
1. Extract candidates
Review the current conversation and identify:
- Decisions — architectural or design choices made with rationale
- Lessons — things that worked or didn't, confirmed assumptions
- Gotchas — surprising behaviors, edge cases, footguns discovered
- Patterns — reusable approaches confirmed in practice
- Limitations — constraints, known issues, things that can't be done
- Breaking changes — API or behavior changes that affect existing code
Be selective — not every exchange is worth persisting. Prefer durable insights over session-specific context. Skip anything that belongs in project files (CLAUDE.md, code comments) rather than the cross-project knowledge graph.
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.
- 7d ago First seen · 230 lines · 147 tokens per session scan A 518ad425ec80
session-reflect is a skill published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 10d ago), licensed MIT. It adds 147 tokens to every session and 2,397 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…
upstream-tracker
Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…
retrospective
Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for…
swarm-wave
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or…
backlog-groomer
Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases…