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 dizeldz20-ux/agent-shared-memory --skill graph-missiongit clone --depth 1 https://github.com/dizeldz20-ux/agent-shared-memoryWrote 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/dizeldz20-ux/agent-shared-memory/graph-mission)<a href="https://agentmods.dev/skills/dizeldz20-ux/agent-shared-memory/graph-mission"><img src="https://agentmods.dev/badge/skills/dizeldz20-ux/agent-shared-memory/graph-mission/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/dizeldz20-ux/agent-shared-memory/graph-mission"><img src="https://agentmods.dev/badge/skills/dizeldz20-ux/agent-shared-memory/graph-mission.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 | $0.00139 | $0.01098 |
| Opus 5.5 | $0.00056 | $0.00439 |
| Sonnet 5.5 | $0.00028 | $0.00220 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
graph-mission 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 29d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph Mission for Codex
Compile the request into a small typed graph before expensive work, then run it. The graph is temporary execution state; ASM and the vault hold durable knowledge.
- ASM recalls what the workspace already knows.
- The mission graph decides what this run still needs to do.
- Current files and live checks establish what is true now.
- ASM write-back makes verified outcomes available to later sessions of any agent.
Activation boundary
Use this skill for an explicit $graph-mission, two or more lanes that write disjoint files, research plus implementation, broad work whose success is not yet pinned down, or work likely to cross a compaction or session boundary.
For one lookup, one localized edit, or a tightly coupled design or refactor, say in one line that a graph would cost more than it saves, then do the work directly (in compile mode, stop there).
Modes
- Compile: a plan request ("plan this", "break this down",
$graph-mission compile). Ends with the brief as the final answer. - Run:
$graph-mission, or a request to do the work. Compiles, then executes without asking "shall I start?"; gates stop the run where they sit in the graph. - Resume: "resume the mission",
$graph-mission resume, or a run file the user names. Continues per run.md.
Workflow
- knowledge-loop.md: recall before decomposing, opening mapped files, or asking the user anything.
- compile.md: the contract, authority boundary, validation list, run file and brief.
- decomposition.md while building the graph: goal-backward nodes, seven kinds, locks, waves. graph-architecture.md picks the cheapest level that fits.
- Mirror the nodes in the plan tool and share the brief. Compile mode stops here.
- run.md: frontier, dispatch, gates, revise loop, lineage, write-back, close-out.
- evidence-gate.md before any node is marked
verified. A child's report is a lead, not proof. - mission-schema.md whenever the run file is written, updated or resumed.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago Changed · +13 lines · +32 tokens per session 93af451c47af
- 1mo ago First seen · 48 lines · 107 tokens per session scan A e6f5becbb0c4
graph-mission is a skill published in the GitHub repository dizeldz20-ux/agent-shared-memory (1 stars, last pushed 3d ago), licensed MIT. It adds 139 tokens to every session and 1,098 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…