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 ThinkfleetAI/memmesh --skill memmesh-integrategit clone --depth 1 https://github.com/ThinkfleetAI/memmeshWrote 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/thinkfleetai/memmesh/memmesh-integrate)<a href="https://agentmods.dev/skills/thinkfleetai/memmesh/memmesh-integrate"><img src="https://agentmods.dev/badge/skills/thinkfleetai/memmesh/memmesh-integrate/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/thinkfleetai/memmesh/memmesh-integrate"><img src="https://agentmods.dev/badge/skills/thinkfleetai/memmesh/memmesh-integrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00197 | $0.01133 |
| Opus 5.5 | $0.00079 | $0.00453 |
| Sonnet 5.5 | $0.00039 | $0.00227 |
| Haiku 4.5 | $0.00020 | $0.00113 |
Grade A, and why
memmesh-integrate 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memmesh-integrate
Wire MemMesh into an existing repo with a goal-driven, test-first pipeline.
Pairs with memmesh-test-integration for verification.
Canonical sources (fetch BEFORE deciding anything)
WebFetch these and cite them in plan.md. They are ground truth — do not
rely on ambient knowledge of the API.
- Docs index (agent-ready): https://docs.memmesh.ai/llms.txt
- Full docs (deep dives): https://docs.memmesh.ai/llms-full.txt
- Platform vs Local: https://docs.memmesh.ai/platform-vs-local
- Published skills to DELEGATE to (don't reimplement call-site patterns):
- SDK:
memmesh-sdk· CLI + MCP:memmesh-cli· MCP loop:memmesh
- SDK:
Integration principles (non-negotiable)
The goal is a PR the maintainers accept without argument.
- Additive, not replacing. If the repo already has a memory / session / user-context layer, MemMesh sits alongside it. The existing system keeps working unchanged.
- Opt-in by default. Gate all new code behind a flag (
MEMMESH_ENABLED=1, a config key, or a strategy selector). Flag unset ⇒ original behavior, byte-for-byte. - No breakage. No removed/renamed exports, no changed signatures, no modified existing tests. All pre-existing tests pass unchanged with the flag both set and unset.
- Minimal dependency surface. Add
@thinkfleet/memory-sdk(hosted) or thememmeshbinary (local) and nothing else. - Separable commits. Code, tests, config/docs in separate commits.
- The null hypothesis wins. If no additive, gated fit exists, exit with a rationale. A bad PR is worse than no PR.
- Backend only. Integration lives in server-side code. Keys never ship to the client.
Pipeline
- Detect the stack (language, test runner, where user/session context is
handled). Record in
.memmesh-integration/detect.md. - Choose surface — ask the user: Hosted (managed,
mm-key, best for prediction/calibration/verticals) or Local (CLI + MCP over SQLite, no key, best for dev tools / offline). Default to Local for CLIs and dev tooling, Hosted for user-facing apps. - Pick the seam. The highest-value seam is usually the request/response
loop around the LLM:
observethe user turn,search/buildContextbefore generating, and — where it adds value —predictthe next action. Write the goal inplan.mdand cite the canonical sources. - Write failing tests first into
.memmesh-integration/and the repo's test dir: (a) flag-off ⇒ behavior unchanged; (b) flag-on ⇒ observe is called with the user turn; (c) flag-on ⇒ retrieved context reaches the prompt. - Implement the smallest gated wiring that makes the tests pass. Delegate
call-site patterns to
memmesh-sdk/memmesh-cli. - Consider the moat. If the app makes a decision about a user/account
(offer, routing, retention), add an optional
predict/predictTargetcall and surface the calibrated confidence + abstention. Never let an abstention crash the flow — treat "I don't know yet" as a first-class branch. - Emit artifacts in
.memmesh-integration/(detect.md,plan.md,changes.md, seed test data) and stop. Then runmemmesh-test-integration.
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 · 87 lines · 197 tokens per session scan A 6f0be50eb9b9
memmesh-integrate is a skill published in the GitHub repository ThinkfleetAI/memmesh (405 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 197 tokens to every session and 1,133 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
source-command-sparc-coder
Migrated source command sparc-coder.
source-command-sparc-tdd
Migrated source command sparc-tdd.
tdd-with-memory
A test-first implementation workflow that recalls past decisions, conventions, and lessons before coding. TDD, or test-driven development, means writing a failing test first, then implementing the code and finally cleaning it up.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
tdd-cycle
Use when implementing any feature or bugfix, before writing implementation code.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.