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 agentmods add skills/nicograef/handbook/prunenpx skills add nicograef/handbook --skill prunegit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/prune)<a href="https://agentmods.dev/skills/nicograef/handbook/prune"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/prune.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.01107 |
| Opus 5 | $0.00043 | $0.00553 |
| Sonnet 5 | $0.00017 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
prune 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 yesterday.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prune
Retire agent state in two layers.
- Mechanical — for a user-invoked
/prune, deletes aged session state without asking, by explicit design.dry-runis the escape hatch. - Semantic — proposes judgment-based deletions behind a multi-select gate.
Workflow
1. Parse arguments
Argument: $ARGUMENTS — the parts combine freely:
| Argument | Meaning |
|---|---|
| (none) | current project, 7-day threshold, delete |
all |
every project slug plus the global session-state classes |
<N>d (e.g. 30d) |
age-threshold override in days (minimum 1) |
dry-run |
preview only, both layers: mechanical report without deleting, semantic findings without the apply step |
2. Resolve context
- Live session id —
$CLAUDE_CODE_SESSION_IDfrom the session environment. - If unset — proceed without it.
3. Mechanical sweep (ungated)
Run the bundled script via the skill's base directory with an explicit interpreter.
Flags are in its own usage line (prune-state.sh, top of file).
- Never use an absolute handbook path.
- Never rely on the execute bit — the plugin cache may not preserve it.
- Pass
--deleteunlessdry-runwas given — do not ask first, for a user-invoked/prune. - The mechanical classes are age-rule-decidable by design.
- What the script may touch, and everything it never touches, is in state-map.md.
- If the machine's layout stops matching the state map, stop and re-verify per its drift rule before trusting the sweep.
- Never bypass the script with ad-hoc
rmon harness state.
4. Semantic review — collect findings
Review the three classes per criteria.md. Every finding carries class, target, cited evidence, and proposed action: delete or update.
5. Gate — multi-select
- Present all findings in one multi-select.
- Tool — a structured question tool if the surface has one.
- Fallback — the formatted options in ../clarify/question-rules.md.
- Each option shows class, target, evidence, and proposed action.
- Overflow — batch across rounds grouped by class when findings exceed the tool's capacity.
- Zero picks — selecting nothing stays a valid outcome in every round.
What ships with it
3 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.
- yesterday Changed · -13 lines 7a42ae0b74cf
- 5d ago First seen · 129 lines · 85 tokens per session scan A fccef312b32b
prune is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 1,107 once invoked, about $0.0004 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
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…