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 skills add implicit-labs/autosymph --skill verify-completion-auditgit clone --depth 1 https://github.com/implicit-labs/autosymphWrote 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/skills/implicit-labs/autosymph/verify-completion-audit)<a href="https://agentmods.dev/skills/implicit-labs/autosymph/verify-completion-audit"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-completion-audit/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/skills/implicit-labs/autosymph/verify-completion-audit"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-completion-audit.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 | $0.00068 | $0.01095 |
| Opus 5.5 | $0.00027 | $0.00438 |
| Sonnet 5.5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
verify-completion-audit 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 2mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-completion-audit
Counts critical tool calls in a verify-run ndjson and asserts the completion contract. Designed to replace the verify_review agent's manual eyeballing of the log with a deterministic check.
When to use
verify_review agent: as the FIRST thing you do after fetching the verify run's ndjson. The audit either confirms the contract is intact (continue with your normal evidence audit) or returns the rejection reasons pre-packaged.
Autosymph monitor / debugging: any time you want to know "did this verify run actually finish, or did it just stop?"
The contract being checked
Verify is considered complete IFF all of these hold:
| Check | Why |
|---|---|
mcp__linear__save_comment count ≥ 1 |
The verification table must reach Linear; without it nothing exists for a human to evaluate |
create_attachment count ≥ screenshot + record_video count |
Every local visual file must be uploaded; orphan local files are wasted work |
If any visual evidence was captured, create_attachment ≥ 1 |
Catches the "took 24 screenshots, uploaded 0" case directly |
The script
${AUTOSYMPH_SKILLS_DIR:-$HOME/.autosymph/skills}/verify-completion-audit/scripts/audit.sh \
<path-to-verify-runN.ndjson>
Output: JSON line first (machine readable), then markdown (paste into Linear).
Exit codes:
0— contract honored (all visual evidence uploaded; summary posted)2— at least one violation; the JSONviolationsarray is the recommendedreject_structifyreasonslist1— usage / file-not-found
How verify_review uses it
# Step 1 of verify_review: download the run's ndjson, audit it.
NDJSON=$(autosymph fetch-ndjson ISSUE-123 verify run10) # or read from logs dir
${AUTOSYMPH_SKILLS_DIR:-$HOME/.autosymph/skills}/verify-completion-audit/scripts/audit.sh "$NDJSON"
case $? in
0) echo "completion contract intact — proceed with evidence audit" ;;
2) echo "completion violations — emit reject_structify with the audit's reasons array" ;;
esac
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 114 lines · 68 tokens per session scan A 31d14a7c4835
verify-completion-audit is a skill published in the GitHub repository implicit-labs/autosymph (5 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,095 once invoked, about $0.0003 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.