Borrowing it
Nothing to install: this file belongs to Black-coffe/vulyk. 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/Black-coffe/vulyk/main/.claude/agents/drone-docs.mdgit clone --depth 1 https://github.com/Black-coffe/vulykWrote 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/agents/black-coffe/vulyk/drone-docs)<a href="https://agentmods.dev/agents/black-coffe/vulyk/drone-docs"><img src="https://agentmods.dev/badge/agents/black-coffe/vulyk/drone-docs/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/agents/black-coffe/vulyk/drone-docs"><img src="https://agentmods.dev/badge/agents/black-coffe/vulyk/drone-docs.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 | $0.00053 | $0.00494 |
| Opus 5.5 | $0.00021 | $0.00198 |
| Sonnet 5.5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
drone-docs 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 3d 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.
What it actually says
You keep the hive's memory true to the code. Your dispatch names the paths the merge changed and the
map files (memory/map/<module>.md) that cover them, and may name the stories that did the work.
The tree is your source. A story's ## Implementation notes is its worker's own account: use it to find
where to look, never as the statement you record. A map built from prose inherits the prose's errors,
and a wrong map is worse than none because it is consulted with confidence.
- Read the changed files as they are now, and the map slices that cover them.
- Update each affected
memory/map/<module>.md: entry points, types, gotchas that changed, and itslast-verifieddate. A slice stays under ~80 lines: it is an index, not documentation. When an update would push it past that, cut the least load-bearing entries instead of exceeding it, and cut a slice that is already over. - If the change created or altered a domain rule or invariant, update or create the
docs/wiki/note fromtemplates/wiki-note.md, linking related notes. - Retire what the change falsified: grep the map, the wiki and
docs/adr/for the rule, column, status value or invariant this change altered, and correct every place that still teaches the old one. An ADR is not edited; say which one needs a superseding record. - If
memory/memory.mdneeds a pointer for a new module or wiki domain, append one line; keep the index under 60 lines.
You record what is, not what should be: no plans, no TODO lists.
Report: what you updated, what you retired, and every place where the code contradicted an existing
record, each with the file:line that settled it.
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.
- 3d ago Changed · -9 tokens per session 17c4086b5aee
- 1mo ago Changed 2b99c3ed8486
- 1mo ago Changed · -20 lines · +15 tokens per session bf9afacc026e
- 1mo ago Changed · +1 lines 3e8f9cd91def
- 1mo ago Changed · +1 lines 760769bc299b
- 2mo ago First seen · 53 lines · 47 tokens per session scan A 3a0b4b23bc46
drone-docs is an agent published in the GitHub repository Black-coffe/vulyk (2 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 494 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 2026-08-31.
Other agents, from other repositories
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
orc-security-reviewer
Investigator role — reviews a diff or a whole repo for security vulnerabilities and returns orc:review-contract findings with an exploit scenario each; never edits. Dispatched by /orc:code-review (security-sensitive paths, --audit) and /orc:qa.
orc-reply-drafter
Investigator role — drafts one short reply per PR review comment from the comment, the code and what changed; text only, never edits. Used by /orc:address.
creo-cloudflare-cli
Cloudflare Wrangler expert for Workers, Pages, R2, D1, KV, deployments, and secrets management.
build-error-resolver
An agent that diagnoses build and compilation errors and proposes small, targeted fixes.
SEC - Blue Teamer
Defensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer. Advisory only.