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 leopu00/job-hunter-team --skill memory-stategit clone --depth 1 https://github.com/leopu00/job-hunter-teamWrote 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/leopu00/job-hunter-team/memory-state)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/memory-state"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/memory-state/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/leopu00/job-hunter-team/memory-state"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/memory-state.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 | $0.00055 | $0.01016 |
| Opus 5.5 | $0.00022 | $0.00406 |
| Sonnet 5.5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
memory-state 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Memoria di stato (variabili tra tick)
Mantieni queste variabili nella tua memoria conversazionale. Le usi per decidere se notificare il Capitano (edge-triggered).
Variabili
last_ordine = {
tipo: "ACCELERA | RALLENTARE | EMERGENZA | RIENTRO | RESET |
MANTIENI | SCALA_UP | PUSH_GSPOT | RECOVERY | STAGNAZIONE |
PEGGIORAMENTO | None",
throttle: 0..4,
usage: int,
proj: float,
ts: "HH:MM:SS",
}
freeze_active = bool # True dopo freeze_team.py
fatal_streak = int # 0/1/2: cicli FATAL consecutivi
tick_steady_count = int # tick consecutivi proj 90-95%
# (per MANTIENI dopo 3)
tick_below_gspot_count = int # tick consecutivi proj 70-90%
# (per PUSH G-SPOT dopo 2)
tick_sotto_count = int # tick consecutivi proj<70 + vel<ideale×0.7
# (per SCALA UP dopo 2)
emergency_proj_history = list # ultimi 5 proj durante zona >100%
# (per RECOVERY TRACKING / STAGNAZIONE)
emergency_proj_min = float # minima proj raggiunta nell'episodio
# (per PEGGIORAMENTO POST-FREEZE)
push_gspot_cooldown = int # cooldown PUSH G-SPOT (0/1/2/3 tick)
scala_up_cooldown = int # cooldown SCALA UP (0/1/2 tick)
recovery_tracking_cooldown = int # cooldown RECOVERY TRACKING (0/1/2/3)
Aggiornamento ad ogni tick
# Pseudocode da eseguire ad ogni [BRIDGE TICK]:
# 1. Cooldown decrement
push_gspot_cooldown = max(0, push_gspot_cooldown - 1)
scala_up_cooldown = max(0, scala_up_cooldown - 1)
recovery_tracking_cooldown = max(0, recovery_tracking_cooldown - 1)
# 2. Counter stato
if status == "STEADY": tick_steady_count += 1
else: tick_steady_count = 0
if 70 <= proj < 90: tick_below_gspot_count += 1
else: tick_below_gspot_count = 0
if proj < 70 and vel < ideale * 0.7:
tick_sotto_count += 1
else: tick_sotto_count = 0
# 3. Memoria emergenza (zona proj > 100%)
if proj > 100:
emergency_proj_history.append(proj)
emergency_proj_history = emergency_proj_history[-5:]
emergency_proj_min = min(emergency_proj_min or float('inf'), proj)
else:
# Uscita zona emergenza: reset
emergency_proj_history = []
emergency_proj_min = None
# 4. Reset event
if last_sample.usage - usage > 30:
reset_session() # azzera storico, manda RESET SESSIONE
What ships with it
6 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.
- 1mo ago First seen · 107 lines · 55 tokens per session scan A dfbe0e733001
memory-state is a skill published in the GitHub repository leopu00/job-hunter-team (52 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,016 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 2026-09-03.
Other skills, from other repositories
screenpipe
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…