Borrowing it
Nothing to install: this file belongs to Foxfire1st/agents-remember. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Foxfire1st/agents-remember/main/.agents/skills/c-00-initialize-memory-repo/SKILL.mdgit clone --depth 1 https://github.com/Foxfire1st/agents-rememberWrote 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/foxfire1st/agents-remember/c-00-initialize-memory-repo)<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-00-initialize-memory-repo"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-00-initialize-memory-repo/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/foxfire1st/agents-remember/c-00-initialize-memory-repo"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-00-initialize-memory-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 185 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 228 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00044 | $0.02375 |
| Opus 5.5 | $0.00018 | $0.00950 |
| Sonnet 5.5 | $0.00009 | $0.00475 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
c-00-initialize-memory-repo 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 2mo 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
c-00-initialize-memory-repo Initialize Memory Repo
Create the minimal memory root required before onboarding or task workflows can use Agents Remember for a target repository.
This skill initializes durable repo memory through MCP memory_init. It does
not install the coordinator runtime, expose harness skills, create task
worktrees, or generate onboarding content. Request MCP runtime_install only
when the coordinator runtime scaffold is missing or stale. Harness skill
exposure for first-run setup comes from the copied starter package, not from
this skill. Use c-03-repo-bootstrap after the memory scaffold exists when the
developer wants onboarding content generated.
Use c-08-ar-coordination-context-resolver to inspect an existing repository's active context. This skill creates or repairs missing memory scaffolding; it does not replace the c-08-ar-coordination-context-resolver skill as the normal resolver.
Inputs
repo_id: configured MCP repository ID whose memory is being initialized. This is the normal installed runtime input.code_repository_root: root directory of the code repository whose memory is being initialized. Use this only for conceptual review or source-debugging; normal installed runtime calls identify the configured repository byrepo_id.topology:internalby default. Useexternalonly when the developer explicitly asks for an external memory repo.coordination_root: supplied by MCP settings for normal installed runtime calls.mode:create-missingby default. Userepaironly when the developer explicitly asks to fix existing memory scaffold files.
MCP Tools
Use the Agents Remember MCP setup tools as the normal installed runtime entry points:
Preview first. These setup tools now apply by default (
dry_rundefaults tofalse). For any effectful run, call once withdry_run=trueto inspect the plan, confirm it, then run the real apply (omitdry_run).
memory_init(repo_id="<repo-id>", dry_run=true, initialize_git=true) # preview
memory_init(repo_id="<repo-id>", initialize_git=true) # apply
runtime_install(include_benchmarks=false, install_provider_deps=false)
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.
- 2mo ago First seen · 319 lines · 44 tokens per session scan A eaa7f69dc1cc
c-00-initialize-memory-repo is a skill published in the GitHub repository Foxfire1st/agents-remember (39 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,375 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 2026-08-30.
c-00-initialize-memory-repo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| c-00-initialize-memory-repoFoxfire1st/agents-remember | Skill | 39 | yesterday | MIT | A | 44 | Claude Code, Codex |
| remember-sessiondoobidoo/mcp-memory-service | Skill | 2.1k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| memwalMystenLabs/MemWal | Skill | 121 | 18d ago | Apache-2.0 | A | 80 | Claude Code, Codex |
| cortex-profilecdeust/Cortex | Skill | 76 | today | MIT | A | 98 | Claude Code |
| cortex-remember-globalcdeust/Cortex | Skill | 76 | today | MIT | A | 99 | Claude Code |
| cortex-consolidatecdeust/Cortex | Skill | 76 | today | MIT | A | 84 | Claude Code |
| cortex-explore-memorycdeust/Cortex | Skill | 76 | today | MIT | A | 91 | Claude Code |