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.
git clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/commands/skyfox675/agents-skills/spelunking-refresh-spec)<a href="https://agentmods.dev/commands/skyfox675/agents-skills/spelunking-refresh-spec"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/spelunking-refresh-spec/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/commands/skyfox675/agents-skills/spelunking-refresh-spec"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/spelunking-refresh-spec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00118 | $0.00812 |
| Opus 5 | $0.00059 | $0.00406 |
| Sonnet 5 | $0.00024 | $0.00162 |
| Haiku 4.5 | $0.00012 | $0.00081 |
Grade A, and why
spelunking-refresh-spec 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 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.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spelunking-refresh-spec — forward-refine the spec set
Operate in caveman mode (load the
cavemanskill). Keep references,file:line, frontmatter, and the_index.mdtable byte-exact; the spec prose is the exception (humanizer — see the spelunking-specs skill).
Arguments: $ARGUMENTS
Parse them as:
- Optional scope: a numeric reference (
1.2.3or a prefix like1.2for a subtree), a domain name/number, or a path. No arg = refresh the specs whoselast_reviewedis stalest or whose source files changed since (git diff/git log). - Optional
model:<tier>/effort:<level>, anywhere — pin the recon agents' tier (defaultsonnet).
Example: /spelunking-refresh-spec 1.2 (the auth subtree) · /spelunking-refresh-spec src/payments · /spelunking-refresh-spec (stalest/changed)
The spelunking-specs skill is the protocol; this command is its forward-refining pass. Consult it before starting.
Steps
-
Resolve scope and read existing specs first. From
_index.md, select the in-scope specs. A refresh is a resume: read each spec and its citedfile:linebefore changing anything — never rewrite from scratch. -
Diff understanding against current code (fan out one agent per spec or per domain, per the dispatching-subagents skill). For each:
- Still accurate → re-verify and update
last_reviewed;draft → verified, orverified → stableif unchanged across passes. - Code changed (intended) → update Discovered behaviour and restate the convention as a refinement, with fresh evidence.
- Code contradicts the spec and looks like a regression → do NOT rewrite the standard to match broken code; flag it in Drift & open questions as a candidate issue.
- New domain/subdomain/instance found → append the next free number, add to
_index.md(never reuse or renumber). - Gone/dead → mark
status: deprecatedwith a pointer to the successor ref; do not delete the reference.
- Still accurate → re-verify and update
-
Verify, don't trust. Re-read cited
file:linefor the claims you touched before flipping any confidence upward; can't re-confirm ⇒ drop todraftwith a note.
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 · 38 lines · 118 tokens per session scan A 227613f68234
spelunking-refresh-spec is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 118 tokens to every session and 812 once invoked, about $0.0006 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.