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/curtisthe/three-pillars-plugin/tp-session-savenpx skills add CurtisThe/three-pillars-plugin --skill tp-session-savegit clone --depth 1 https://github.com/CurtisThe/three-pillars-pluginWrote 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/curtisthe/three-pillars-plugin/tp-session-save)<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-session-save"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-session-save.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 | $0.00033 | $0.00886 |
| Opus 5 | $0.00016 | $0.00443 |
| Sonnet 5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
tp-session-save 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Compact
Write a structured handoff that captures what compaction and memory would lose — the why behind decisions, not just the what.
Argument: {design-name} (required) — must match an existing directory under three-pillars-docs/tp-designs/.
Top-level / cross-design work (fleet launches, merge-queue drains, multi-design campaigns) has no single design dir — save it under the reserved
orchestrationslot (/tp-session-save orchestration). It is not a design (nodesign.md/ lock / branch), so/tp-design-completenever archives it out from under you. Seethree-pillars-docs/tp-designs/orchestration/README.md.
Steps
-
Run first-run preflight per skills/_shared/first-run.md.
-
Resolve the design directory:
three-pillars-docs/tp-designs/{design-name}/. If it doesn't exist, tell the user no design by that name exists and stop. -
Read the existing handoff at
three-pillars-docs/tp-designs/{design-name}/handoff.md(if it exists). Note anything still relevant — you'll carry it forward. Everything else is discarded. -
Review this conversation — what was discussed, decided, built, and left unfinished.
-
Overwrite
three-pillars-docs/tp-designs/{design-name}/handoff.mdentirely with fresh content from this session. The new file is the source of truth — the old one is gone. Use these sections:
## Phase
What phase/task the user was working on. One line.
## Decisions
Bulleted list of non-obvious decisions and trade-offs made this session.
Skip anything already visible in code diffs or commit messages.
## State
What's done, what's half-done, what's blocked.
Be specific: file names, function names, test results, branch state.
## Next
What the user will likely want to do next. Ordered by priority.
## Open Questions
Unresolved items to raise next session.
## Carried Forward
Any still-relevant context from the prior handoff (max 5 lines).
Drop anything superseded by this session's work.
- Update the MRU. Run the MRU snippet from
skills/_shared/validate-name.mdwithname={design-name}so the first line of.claude/last-designis the design you just saved — saving a session is using it. This is what lets a later/clear+/tp-session-restore(no argument) resolve back to this design (or to theorchestrationslot for fleet / cross-design sessions). Nevergit addthe file (it's gitignored).
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 · 58 lines · 33 tokens per session scan A f5f3f70fa026
tp-session-save is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 886 once invoked, about $0.0002 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…