Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. 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/zkysar1/Claude-Mind/main/.claude/skills/aspirations-precheck/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/aspirations-precheck)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/aspirations-precheck"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/aspirations-precheck/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/zkysar1/claude-mind/aspirations-precheck"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/aspirations-precheck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
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 →
- medium Excessive Agency · line 1675 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 1810 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 1813 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 1815 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 1818 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.
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 | $0.00097 | $0.33772 |
| Opus 5 | $0.00048 | $0.16886 |
| Sonnet 5 | $0.00019 | $0.06754 |
| Haiku 4.5 | $0.00010 | $0.03377 |
Grade A, and why
aspirations-precheck 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 4d 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 — 2,061 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aspirations-precheck — Pre-Selection Checks
Runs all checks that must happen BEFORE goal selection each iteration. Ensures completion runners fire, aspiration health is maintained, guardrails are checked, blockers are resolved, and recurring goals are tracked.
Step 0: Load Conventions — Bash: load-conventions.sh with each name from the conventions: front matter.
Step 0-open: RUN THE ENTRY BATTERY FIRST (g-115-6468) — one call that IS the
executor for Step 0a's meter start, the entry checks, and every always-run and
medium lane, then prints a per-stage rc table, FINDINGS ONLY, selection
candidates, and a NEXT ACTION REQUIRED: imperative. Lane counts are DERIVED —
never re-type one here.
Bash: bash core/scripts/iteration-open.sh --apply
It SUBSUMES Step 0a and both the always-run AND medium phase bodies below — do
NOT also run them, or the --apply lanes escalate twice. Dispose what it prints,
then resume at the first deferrable sweep. Run the standalone fallback
(tier table) on wrapper_failed, on a BLIND stage, and on a KILLED run — which
reports NEITHER, so judge by rc AND bytes, not output: empty stdout at rc≠0 is
BLIND, not clean, and stderr's last -> crumb names the stage in flight
(g-115-7844). --dry-run lists lanes and wiring status; an undispatched one
prints not-yet-wired, not nothing. The deferrable tier is NOT yet
wired (strangler step 3).
⚠ That sentence does not MAKE anything run — its twin said "medium" while that tier sat dark 94-208h on two boxes (g-115-7847). Tiers run by being STAGES in iteration-open.sh.
Rationale, composition contract, worker-vs-reducer meter split: the
core/scripts/iteration-open.py docstring; dark-window trace and
execution-record design: core/scripts/precheck-medium-battery.py.
Step 0a: Budget Meter Start (Magic Wand 2 — g-115-509) — fallback only when
Step 0-open did not run; it calls this itself. Initialize the
precheck cost meter. The meter returns "drop" for deferrable sweeps ONLY when
the zone is tight (zone_drop_rules.tight). Always-run sweeps (Phase 0-pre,
0-pre2, 0-pre3) NEVER drop. The former wall-clock budget-overrun drop path was
REMOVED (g-115-1489 — elapsed measured inter-tool-call LLM latency, not script
cost, so it dropped EVERY deferrable sweep every iteration and starved the
fresh-eyes/felt-sense/health-regression cadence rituals). elapsed-ms is still
logged for telemetry. Decisions log to agents/<agent>/session/precheck-drops.jsonl.
Bash: bash core/scripts/aspirations-precheck-budget-meter.sh start
Before any sweep that the table below marks as medium or deferrable, call
meter check <sweep-name> and skip the phase when the response is drop.
Always-run sweeps skip the check (they never drop). At the bottom of this
SKILL.md (after Phase 1) call meter end to write the summary record.
The Invocation column is the exact command (g-115-6207 — 4 of the names
below did NOT resolve to a runnable command by name alone, and every one of
those failures prints to stderr and exits non-zero, which a batched
2>/dev/null loop renders as an empty-stdout all-clear). Sweep NAME ≠ script
name for the two reclaim rows; subcommands are REQUIRED where shown; the
sentinel/cadence/always-run battery rows are dispatched by their battery, not
standalone scripts. The always-run rows also name a standalone fallback — those
scripts DO exist independently and are what a blind battery falls back to; the
column half is not a duplicate. Phase bodies below remain the authority on flags (--apply forms);
this column mirrors them. rc convention: rc=1 is AMBIGUOUS. precheck-eval
run-all exits 1 on ACTIONABLE FINDINGS; l1-skew-check --cadence exits 1 with
ZERO output as a documented silent noop. Judge by OUTPUT, not rc alone.
Every invocation below was run 2026-08-14 with rc recorded (report forms).
Deferrable phase BODIES live in a digest (g-115-6583). The table above is the index and carries each lane's exact Invocation, so the common path needs no load. Load the digest when a deferrable lane needs its full body — measured markers, parse-shape warnings, incident traces:
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.
- 4d ago Changed · +8 lines aec1e6b97a0b
- 9d ago Changed · -815 lines f062258f4ac1
- 12d ago First seen · 2,868 lines · 97 tokens per session scan A 273d195783fb
aspirations-precheck is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 33,772 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.