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 carsteneu/yesmem --skill yesresearchgit clone --depth 1 https://github.com/carsteneu/yesmemWrote 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/carsteneu/yesmem/yesresearch)<a href="https://agentmods.dev/skills/carsteneu/yesmem/yesresearch"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesresearch/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/carsteneu/yesmem/yesresearch"><img src="https://agentmods.dev/badge/skills/carsteneu/yesmem/yesresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 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 Tool Misuse · line 1031 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 6 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 50 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 52 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 128 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 475 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 144 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 227 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 456 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 685 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- low Excessive Agency · line 1204 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00087 | $0.16517 |
| Opus 5 | $0.00044 | $0.08259 |
| Sonnet 5 | $0.00017 | $0.03303 |
| Haiku 4.5 | $0.00009 | $0.01652 |
Grade A, and why
yesresearch scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(git *) Bash(curl *) Bash(pdftotext *) Bash(mkdir *) Bash(ls *) Bash(cat *) Bash(find *) Bash(rg *) Bash(test *) Grep Glob Read Write Edit todowrite Task How it starts
The opening of the file, as written. The whole thing — 1,219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Research Loop
You are an orchestrator for autonomous research. Decompose a research topic into clusters, spawn parallel research agents, integrate results into a cited wiki.
CRITICAL: Two-Tier Architecture
You are the Orchestrator (this session). You do NOT do research yourself. You spawn Bereichs-Agents (cluster agents) that do the actual research work. Each Bereichs-Agent runs autonomously in its own worktree and reports progress via scratchpad.
Orchestrator (this session, light)
│
├─ READ master-plan (## headings = clusters)
├─ DECOMPOSE into 5-8 file groups
├─ DISPATCH yesmem_spawn_agent × ≤6 (opencode TUI agents)
├─ MONITOR list_agents + scratchpad polling
├─ INTEGRATE cross-links + INDEX.md + citation audit
└─ DELIVER commit + DONE
│
▼ yesmem_spawn_agent (TUI, max 12h, ≤6 concurrent)
│
Bereichs-Agent (full TUI, autonomous)
├─ CONTEXT read master plan + cluster files
├─ PLAN set_plan, per-file strategy
├─ EXECUTE task(general) fetch+search+write
│ task(explore) read-only citation review
│ bash+curl+pdftotext for PDFs
├─ VERIFY min 2 sources/file, every claim cited
├─ COMMIT write files to worktree
└─ DELIVER scratchpad DONE + send_to orchestrator
Why two-tier: Sawtooth would compress the master plan if one agent did everything. Cluster-scope agents keep context small. Plan lives in DB (scratchpad + set_plan), survives collapse.
CRITICAL: Always spawn in a worktree
When invoked from an interactive session, the user's session only does setup — it does NOT run the orchestrator pipeline inline. Setup creates the worktree, writes the master plan + scratchpad briefing, then spawns the Orchestrator as a TUI agent which takes over all 6 phases.
Setup steps (user's interactive session):
- Create worktree:
git worktree add -b yesresearch/<topic-slug> <repo>/.worktrees/yesresearch-<topic-slug>(fresh-create) ORgit worktree add -b yesresearch/<topic-slug>-update-N <repo>/.worktrees/yesresearch-<topic-slug>-update-N(update mode, branching from previous wiki commit) - Write master plan to
<worktree>/yesdocs/<topic>/PLAN.md(or pass existing path) - Detect model & backend: Read
~/.config/opencode/opencode.json→ extractmodelkey (e.g.deepseek/deepseek-reasoner). If absent, detect from opencode's default (first entry in models.json). Backend defaults to"opencode"— override via scratchpad briefingbackend: claude|codex|opencodeor master plan frontmatter. Both model and backend are passed to ALL spawns (Orchestrator + Bereichs-Agents). - Write Orchestrator briefing to scratchpad section
yesresearch-<topic-slug>-orchestrator: worktree path, master plan path, output target, hard constraints, resolved model, mode (fresh-create or update). The briefing MUST start with the skill-read mandate:YOU ARE A YESRESEARCH-ORCHESTRATOR. MANDATORY - YOU MUST READ THE YESRESEARCH SKILL AND YOU MUST FOLLOW THE INSTRUCTIONS IN THIS SKILL.The spawned Orchestrator has NOT auto-loaded this skill — the mandate prefix is mandatory. - Spawn Orchestrator:
yesmem_spawn_agent(project="<project>", section="yesresearch-<topic-slug>-orchestrator", backend="<resolved-backend>", work_dir="<worktree-path>", model="<resolved-model>") - Wait 15s, then relay kick:
yesmem_relay_agent(to="<orchestrator-id>", content="Read scratchpad section yesresearch-<topic-slug>-orchestrator AND load the yesresearch skill (skill tool or ~/.claude/skills/yesresearch/SKILL.md). MANDATORY - YOU MUST READ THE YESRESEARCH SKILL AND YOU MUST FOLLOW THE INSTRUCTIONS IN THIS SKILL. Begin Orchestrator Phase 1 READ.")— backup if PTY is slow - User's session polls
list_agents+scratchpad_readuntil Orchestrator reports DONE.
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.
- 9d ago First seen · 1,219 lines · 87 tokens per session scan A ba25488b5f30
yesresearch is a skill published in the GitHub repository carsteneu/yesmem (41 stars, last pushed 6d ago), licensed Apache-2.0. It adds 87 tokens to every session and 16,517 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks the linked issue, required tests and docs, then writes Description / Proofs / Fixes.
shelve
Offload a closed conversation topic (or a whole imported dialog) to the memory shelf as a Markdown episode with a validated digest. Use when a topic is finished, when context grows heavy, before compaction, or when the user asks to shelve/archive part of the conversation. M0 prompt-only version — the agent does the…
lithium-kb
Generates, maintains, and visualizes a structured Markdown knowledge base (.lithium-kb/{architecture,debug,tasks,features}) with an interactive Neural Network graph, auto-watch mode, custom agent directives (.agentrules), and MCP server integration for Pi, Claude, Codex, Cursor, and other coding agents. Triggers…
hypermnesic-memory
Use when Hermes needs durable project or personal memory through the local hypermnesic CLI: retrieve prior context, think through related notes, resolve entities, inspect writable folders, capture notes, or preview guarded writes.
graphifychat
Turn any conversation into a queryable knowledge graph. Three-layer portable memory file: TRON (structured input+output capture with emotion, psychology, intent — every turn), Sparse6 (layered relational graph with community detection, hyperedges, confidence scores — every turn), GRAPHREPORT (god nodes + surprising…