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/terva-sh/terva/code-reviewnpx skills add terva-sh/terva --skill code-reviewgit clone --depth 1 https://github.com/terva-sh/tervaWhat 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 | $0.00015 | $0.00434 |
| Opus 5 | $0.00008 | $0.00217 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
code-review 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.
This is a copy
100% identical to code-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Code review
When the user asks for a code review (and you have not already done one in this turn), follow this routine.
1. Establish what changed
Use bash to run git status and git diff (or git diff --staged
if there are no unstaged changes). Skim the patch end to end before
analysing any single hunk.
2. For each modified file
Read the file in full with the read tool — never review only the
hunk; you need surrounding context to evaluate the change properly.
Then look for:
- Correctness: bugs, off-by-one errors, wrong sign, missing nil checks, swapped arguments, race conditions.
- Error handling: every external call (file IO, network, parsing, syscalls) — does it propagate or swallow? Are errors wrapped with enough context?
- Tests: do the new code paths have tests? Are existing tests still passing what they claim?
- Surface area: are exports necessary, or could the change stay internal? Public APIs deserve more scrutiny than internals.
- Style consistency: does the change match neighbouring code?
3. Report
Produce a concise written review with this shape:
- Verdict (one line): ship-as-is / minor changes / needs work / blocked.
- Required changes (numbered, if any).
- Suggestions (bullets, optional).
- Praise (one or two lines if anything stood out — keeps the feedback humane).
Don't restate every line of the diff. Don't speculate about future features. Stay grounded in what the patch does.
4. Stop
Do not auto-apply fixes. The user will decide what to act on.
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 · 53 lines · 15 tokens per session scan A 48ec53b0e947
code-review is a skill published in the GitHub repository terva-sh/terva (2 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 434 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to code-review, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
release
Create a new versioned release with changelog. Bumps version in code, updates CHANGELOG.md, commits, tags, and pushes using the repository release flow. GitHub Actions creates the release and uses only the current changelog section as release notes. Use when the user says "release", "cut a release", "bump version"…
qa
Regression test a San feature by name. Looks for a feature doc in docs/reference/ or docs/packages/2-feature/, runs automated Go tests and interactive tmux tests, then produces a pass/fail report. Use this skill when the user says "qa", "regression test", "test feature X", "verify feature", or references a feature…
pi-sync
Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.
dream-memory
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
kairos-lite
Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.
memory-extractor
Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.