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 danielvm-git/bigpowers --skill session-stategit clone --depth 1 https://github.com/danielvm-git/bigpowersWrote 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/danielvm-git/bigpowers/session-state)<a href="https://agentmods.dev/skills/danielvm-git/bigpowers/session-state"><img src="https://agentmods.dev/badge/skills/danielvm-git/bigpowers/session-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/danielvm-git/bigpowers/session-state"><img src="https://agentmods.dev/badge/skills/danielvm-git/bigpowers/session-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00041 | $0.01589 |
| Opus 5.5 | $0.00016 | $0.00636 |
| Sonnet 5.5 | $0.00008 | $0.00318 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
session-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 1mo 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story: e45s23
Session State
HARD GATE — HARD GATE — Session state must be synchronized with git state. If state.yaml conflicts with the working tree, halt and ask for clarification. Do NOT assume state is correct.
Track the current state of implementation, including decisions made, pending tasks, and open questions, to ensure continuity across session boundaries and prevent "context rot."
Session-state implements the isolate strategy from the context-engineering framework (docs/references/context-engineering.md): each agent gets exactly the context it needs — no more — by recording decisions so the next agent can cold-start without replaying history. The four strategies (write, select, compress, isolate) work together: session-state handles isolation, terse-mode handles compression, survey-context handles selection, and CONVENTIONS.md ensures token-efficient writing.
Goal
Maintain a single source of truth for the current session in specs/state.yaml. This complements long-term docs in specs/tech-architecture/ and delivery detail in specs/epics/ + specs/release-plan.yaml.
Legacy markdown (specs/archive/STATE.md, RELEASE-PLAN.md) is not SoT when YAML exists — use specs/state.yaml only.
When a story modifies existing behavior, patch only between matching marker pairs in CLAUDE.md / AGENTS.md learned-preferences fence — see e45s21.
Handoff block (cold start)
When ending a session or before a context-heavy spawn, update handoff in state.yaml:
handoff:
last_step_completed: "e02s01 verify-work passed"
open_decisions:
- "Use folder mode for e07 (>5 stories)"
required_reading:
- CONVENTIONS.md
- specs/epics/e02-verification/epic.yaml
next_skill: develop-tdd
Strategic compaction
| Trigger | Action |
|---|---|
| Phase transition (Plan → Build → Verify) | Compact handoff; archive verbose decisions to ADR |
| Context > 70% estimated | Run terse-mode for status only; move detail to specs/ |
Before dispatch-agents wave |
state.yaml only channel between spawns |
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.
- 1mo ago First seen · 147 lines · 41 tokens per session scan A 5c41823c636e
session-state is a skill published in the GitHub repository danielvm-git/bigpowers (269 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,589 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
ponytail-debt
Harvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
rem-page-org
What an organisation's page in the notebook is made of — the fixed sections, when a company earns a page at all instead of staying a field on a person's, and the rules that keep it from becoming a second copy of everyone who works there. Composed into every stage that writes one.
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
memory-tasks
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph.