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/icloudza/algokiller-plugin/ciphertextnpx skills add icloudza/algokiller-plugin --skill ciphertextgit clone --depth 1 https://github.com/icloudza/algokiller-pluginWhat 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 | $0.00040 | $0.00466 |
| Opus 5 | $0.00020 | $0.00233 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
ciphertext 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 2d 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 are now entering AlgoKiller ciphertext-recovery mode. High-discipline analysis; drift = hallucination.
MANDATORY FIRST STEPS — execute in order:
-
Load the full methodology from the
ak:ciphertext-recoveryskill. Read it completely before any tool call. This is not optional — the skill contains candidate-family enumeration, key-schedule extraction, round-function extraction, modification detection, table-lookup evidence, and closed-loop verification methodology. -
Parse the user input below. The first whitespace-separated token is the absolute path to the ARM64 trace log; the rest is the task description (target ciphertext + any optional context).
-
Call MCP tool
ak.bind_tracewith that path andmode="ciphertext". Do not proceed if bind fails. -
Proceed with the methodology from the skill. Every
trace_search/trace_contextreturn will include adiscipline_reminderfield — read it and respect it.
NON-NEGOTIABLE RULES (skill expands each):
- Earliest hit = candidate, not conclusion. Verify it sits on the upstream data-flow of the target ciphertext.
- Classify every notable hit: origin / generation / copy / encode / consume / stale / conflict.
- Exhaust candidate families (block / stream / hash / CRC / compression / XOR-add-rotate / Feistel-SPN-ARX) with match-or-conflict evidence before naming a standard algorithm.
- Backward chain-chasing: hard limit 3 hops.
- Input contract: only target ciphertext is guaranteed. Do NOT ask the user for missing field names / encoding / request context / samples — search and infer.
- Sufficient evidence →
write_artifactrecovered Python (.py) + analysis report (.md). - Partial evidence → deliver confirmed + high-confidence + open gaps. Don't stall.
User input:
$ARGUMENTS
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.
- 2d ago First seen · 33 lines · 40 tokens per session scan A ae55dc1d548c
ciphertext is a skill published in the GitHub repository icloudza/algokiller-plugin (77 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 466 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
hexwitness
Investigate authorized binaries and runtime behavior with HexWitness's durable evidence MCP and optional Binary Ninja or IDA live tools. Use for function or class discovery, UUID and field mapping, protocol reconstruction, capture comparison, contradiction analysis, evidence-gap planning, and promotion of live…
liveagent-code-review
Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.
deploy
Trigger the claude-desktop-extra Build & Release GitHub Actions pipeline (build-and-release.yml). With no argument the skill inspects the changes since the last release and decides forcerebuild itself; "/deploy force" / "/deploy no-force" override.
sessions
Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior…
discover-interview-synthesis
Synthesizes user research interviews into actionable insights, patterns, and recommendations. Use after conducting user interviews, customer calls, or usability sessions to extract and communicate findings across participants. Distinct from foundation-meeting-recap, which summarizes one internal meeting for its…
define-jtbd-canvas
Creates a Jobs to be Done canvas capturing the functional, emotional, and social dimensions of a customer job. Use when deeply understanding customer motivations, designing for jobs, or reframing product positioning.