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 adtn0810/truestack --skill truestack-project-memorygit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-project-memory)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-project-memory"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-project-memory/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/adtn0810/truestack/truestack-project-memory"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-project-memory.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 | $0.00096 | $0.01643 |
| Opus 5 | $0.00048 | $0.00822 |
| Sonnet 5 | $0.00019 | $0.00329 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
truestack-project-memory 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 10d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-project-memory
Memory that lives in the repo, not in the model — committed, portable, and reviewable like
code. Before guessing how a project works, read its memory; if it doesn't exist yet, study
the repo and build it before doing substantial work. The other skills
(truestack-architecture-planning, truestack-backend-development, truestack-root-cause-debugging, truestack-quality-control, truestack-react-frontend, truestack-mcp-integration) all read
this first.
When to run
- First substantial task in a repo, or no memory folder exists → study, then build it before the work.
- A command, convention, or risk turns out to be wrong or missing.
- The user asks to set up project memory, onboard the repo, or remember something about the project.
Golden rule: store only what the code can't tell you
Memory captures what isn't derivable from the codebase itself. Do not copy in code
patterns, architecture visible in the code, git history, or routine bug fixes — reading the
code or git log already gives those. Memory is for the non-obvious: why a decision was
made, a convention you can't see, a gotcha that bit you. This keeps memory small and true.
How to build it (study pass)
Derive every fact from the repo — never invent. Inspect package/manifest files, config,
scripts, existing tests, CI, and the directory layout. Record only what you can verify; mark
genuine unknowns as TODO. Write it in plain, skimmable language (short lines, lists, small
tables) so a human reads it as fast as the agent.
Structure
CLAUDE.md # auto-loaded index. Keep UNDER ~120 lines — adherence drops past
# that. Holds: one-line project summary, key commands, the
# Principles and Boundaries blocks, the six seed contracts
# (references/seed-blocks.md), and pointers to the files below.
.ai/memory/
├── project-profile.md # stack, full commands, code map, conventions, verification strategy
├── architecture.md # non-obvious decisions + why (ADR-lite)
└── lessons.md # non-obvious FUNCTIONAL-bug gotchas (one line each), written by truestack-root-cause-debugging
What ships with it
2 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.
- 10d ago First seen · 109 lines · 96 tokens per session scan A ae2b0c12bc7b
truestack-project-memory is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,643 once invoked, about $0.0005 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
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…
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.