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 freedomw1987/tree_monstor --skill dav-jev-oraclegit clone --depth 1 https://github.com/freedomw1987/tree_monstorWrote 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/freedomw1987/tree_monstor/dav-jev-oracle)<a href="https://agentmods.dev/skills/freedomw1987/tree_monstor/dav-jev-oracle"><img src="https://agentmods.dev/badge/skills/freedomw1987/tree_monstor/dav-jev-oracle/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/freedomw1987/tree_monstor/dav-jev-oracle"><img src="https://agentmods.dev/badge/skills/freedomw1987/tree_monstor/dav-jev-oracle.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 | $0.00121 | $0.01586 |
| Opus 5.5 | $0.00048 | $0.00634 |
| Sonnet 5.5 | $0.00024 | $0.00317 |
| Haiku 4.5 | $0.00012 | $0.00159 |
Grade A, and why
dav-jev-oracle 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 6d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
56 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.
- api-contract.md 6.8 KB
- examples.md 10 KB
- jev-oracle.md 10 KB
- output-format.md 2.7 KB
- PoC/.env.example 963 B
- PoC/.gitignore 184 B
- PoC/ac_schema.py 3.8 KB runs code
- PoC/batch_report.py 16 KB runs code
- PoC/cache-fixtures/8b68c2cc7c16c510.json 573 B
- PoC/cache-fixtures/bbfaa5bfe583507a.json 1.9 KB
- PoC/cache-fixtures/README.md 5.4 KB
- PoC/example_run.py 5.7 KB runs code
- PoC/fix_proposal_v2.py 8.9 KB runs code
- PoC/fix_proposal.py 13 KB runs code
- PoC/fixtures/ac/US-101.md 1.5 KB
- PoC/fixtures/ac/US-M62.md 2.7 KB
- PoC/fixtures/ac/US-M63.md 3.0 KB
- PoC/fixtures/ac/US-M71.md 2.4 KB
- PoC/fixtures/ac/US-M81.md 1.9 KB
- PoC/fixtures/US-101-run.json 8.0 KB
- PoC/fixtures/US-101.yaml 1.9 KB
- PoC/fixtures/US-M63-ambiguous-test.py 30 B runs code
- PoC/fixtures/US-M63-ambiguous.py 30 B runs code
- PoC/fixtures/US-M63-apply-test.py 60 B runs code
- PoC/fixtures/US-M63-cleanup-test.py 28 B runs code
- PoC/fixtures/US-M63-dryrun-test.py 32 B runs code
- PoC/fixtures/US-M63-json-test.py 28 B runs code
- PoC/fixtures/US-M63-missing-test.py 20 B runs code
- PoC/fixtures/US-M63-sample.py 49 B runs code
- PoC/flaky_check.py 6.5 KB runs code
- PoC/flaky_integration.py 6.7 KB runs code
- PoC/gh_pr_comment.py 5.5 KB runs code
- PoC/jev_oracle.py 13 KB runs code
- PoC/journey_gen.py 2.3 KB runs code
- PoC/journey_generator.py 10 KB runs code
- PoC/journey_runner.py 21 KB runs code
- PoC/journeys/US-101.yaml 3.5 KB
- PoC/journeys/US-M62.yaml 4.8 KB
- PoC/journeys/US-M63.yaml 5.6 KB
- PoC/patch_parser.py 9.2 KB runs code
- PoC/playwright_observer.py 11 KB runs code
- PoC/playwright_patcher.py 6.9 KB runs code
- PoC/prompts/fix_relay.md 3.5 KB
- PoC/re_validate.py 6.6 KB runs code
- PoC/README.md 10 KB
- PoC/requirements.txt 1.1 KB
- PoC/run_ci.sh 11 KB runs code
- PoC/run_journey.py 5.9 KB runs code
- PoC/run_pipeline.sh 7.5 KB runs code
- PoC/run_report.py 318 B runs code
- PoC/sandbox_runner.py 14 KB runs code
- PoC/setup-venv.sh 10 KB runs code
- tests/poc-bootstrap.bats 21 KB
- tests/poc-clean-clone.bats 15 KB
- tests/poc-venv-guard.bats 15 KB
- tests/v2.1-jev-poc.bats 71 KB
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.
- 6d ago Changed · -53 lines · -36 tokens per session f6b7a41d2f58
- 7d ago First seen · 100 lines · 157 tokens per session scan A c263c6f694c3
dav-jev-oracle is a skill published in the GitHub repository freedomw1987/tree_monstor (2 stars, last pushed 2d ago), with no licence file. It adds 121 tokens to every session and 1,586 once invoked, about $0.0005 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 2026-10-28.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
validate-fix
Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.