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 commands/akasecurity/ai-tc/setupgit clone --depth 1 https://github.com/akasecurity/ai-tcWhat 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 | $0.00017 | $0.11823 |
| Opus 5 | $0.00009 | $0.05912 |
| Sonnet 5 | $0.00003 | $0.02365 |
| Haiku 4.5 | $0.00002 | $0.01182 |
Grade B, and why
setup scanned grade B with 2 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/akasecurity/ai-tc/bin-latest/tools/installer/install.sh | sh Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/akasecurity/ai-tc/bin-latest/tools/installer/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 895 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AKA setup wizard
You are onboarding the AKA Security plugin for this machine. AKA works
fully locally with zero backend and zero Docker: detection runs in-process
and findings persist to a local SQLite store at ~/.aka/data/aka.db.
This wizard tells a calibration story: introduce AKA → show what it does → offer one retroactive scan → report the real numbers it found and the posture it recommends → apply on confirmation → show the installed summary → hand off to the dashboard. Everything the user sees is derived from their actual history — never a fabricated or demo number. When there isn't enough history to judge, the wizard falls back to a conservative severity-derived floor instead of guessing.
The false-positive/severity judgment needs the raw (unmasked) findings to rate
them accurately, so it sends them to the model API through separate claude
CLI subprocesses (a large history is judged in several batches). Per finding it
sends the raw value; about 120 characters of the surrounding transcript
text on either side of it, re-scanned first so every secret AKA's rules detect
in that window is masked — including the finding's own value where it appears
there, which leaves the raw value itself as the only raw text that crosses; and
the finding's non-sensitive labels (rule id, category, severity, the masked
value, the confidence score, and a counter the model echoes back). The source
transcript's path never crosses. Those subprocesses ask the claude CLI to
write no transcript, so the raw values do not enter this conversation or your
scannable history — but a copy of them does leave the machine, sent to the
model provider like any other Claude prompt. You act only on the raw-free plan
the subprocesses print back.
That send takes two separate consents, collected at two different points and neither implying the other: the historical-read grant in step 1 (may AKA read past transcripts at all) and the model-judge grant in step 3 (may what it found be sent to the model API). Each is stated plainly before its own picker, and the judge refuses to run without the step-3 grant. The vault grant in step 1b is a third, separate question about local custody — it authorizes no send, and nothing about it changes what leaves the machine.
Follow the steps below in order. Nothing is written to the policy store until step 5 (or a floor fallback in step 3 if the calibration can't complete).
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 · 895 lines · 17 tokens per session scan B cd85739675d1
setup is a command published in the GitHub repository akasecurity/ai-tc (10 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 11,823 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
cross-validate
Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.
translate-id
Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…
discover
Search the Everruns(Dev) API catalog for available operations.
fix
Universal debugging and fix application with semantic code analysis.
gsd:settings
Configure GSD workflow toggles and model profile.