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 XAIHT/Tlamatini --skill tlamatini_exec_report_row_addergit clone --depth 1 https://github.com/XAIHT/TlamatiniWrote 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/xaiht/tlamatini/tlamatini_exec_report_row_adder)<a href="https://agentmods.dev/skills/xaiht/tlamatini/tlamatini_exec_report_row_adder"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/tlamatini_exec_report_row_adder/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/xaiht/tlamatini/tlamatini_exec_report_row_adder"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/tlamatini_exec_report_row_adder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01001 |
| Opus 5 | $0.00021 | $0.00500 |
| Sonnet 5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
tlamatini-exec-report-row-adder 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 10d 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
Exec Report row adder
Read this first — capture is ALREADY automatic (2026-06-07). EVERY wrapped
chat_agent_*is captured by_resolve_exec_report_specwith no code at all, observational/output and read-only agents INCLUDED. This procedure is an OPTIONAL refinement: use it only to merge a sharedagent_key(a direct@tool+ its wrapped launch), fix the display casing, or give the table a CSS-matched caption gradient. A missing entry does NOT hide an agent.And it never sets the row's colour. SUCCESS/FAILED is decided by
agent/agent_verdict.pyfrom the agent's OWNINI_SECTIONself-report, which OUTRANKS the process exit code. Its CLOSED vocabulary has five disjoint sets: diagnostic-completed and work-completed statuses are green; degraded, work-not-done, and agent-error statuses are red. A completed read-only diagnostic must stillsys.exit(0). Never write a numeric return code instatus:; emitreturncode,success, and a semantic status token. Never add a special case tomcp_agent.pyor re-inline any vocabulary set — there is exactly ONE definition inagent_verdict.py, guarded byagent/test_status_vocabulary.py.
Three-step procedure (matches docs/claude/exec-report.md):
-
Add an entry to
_EXEC_REPORT_TOOLSinTlamatini/agent/mcp_agent.py:"${input.tool_name}": ("${input.agent_key}", "${input.agent_display}"), -
Add CSS rules in
agent_page.css:.exec-report-caption-${input.agent_key}(gradient mirroring.canvas-item.${input.agent_key}-agentfrom agentic_control_panel.css).exec-report-${input.agent_key} .exec-report-cmd { border-left: 3px solid <primary>; }- If the caption is dark, append
.exec-report-${input.agent_key} thead thto the dark-tinted override selector list.
-
Run
python Tlamatini/manage.py test agent.tests.ExecReportCaptureTests agent.test_agent_verdict agent.test_exec_report_verdict agent.test_status_vocabulary. Report the pass/fail status. If the verdict/colour logic was touched at all, also runagent.test_agent_verdictandagent.test_exec_report_verdict.
Return { rows_added, tests_pass }.
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.
- 10d ago First seen · 81 lines · 42 tokens per session scan A 9cecda3a8157
tlamatini-exec-report-row-adder is a skill published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,001 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
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
commit
Inspect git status, draft a commit message that matches the repo's style, and commit staged changes.
review
Review current code changes for bugs, regressions, test gaps, and project-guideline violations.
tura
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
grade-and-fix-daedalus
How to grade a Daedalus run (or pasted agent transcript), root-cause the failure, and ship the fix to Daedalus CORE as a stacked PR — without modifying the prompt-vault sandbox (read-only grading). Covers recurring bug archetypes (Unicode punctuation patch mismatch, syntax-vs-type mislabel, emoji box misalignment…
add-slash-command
How to add a new slash command to Daedalus (src/commands), including the docs-sync step that breaks CI if skipped.