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 ThomasMoreAI/legal-skills-open --skill colombia-conflict-broomvagit clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/colombia-conflict-broomva)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/colombia-conflict-broomva"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/colombia-conflict-broomva/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/thomasmoreai/legal-skills-open/colombia-conflict-broomva"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/colombia-conflict-broomva.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 | $0.00404 | $0.02610 |
| Opus 5.5 | $0.00162 | $0.01044 |
| Sonnet 5.5 | $0.00081 | $0.00522 |
| Haiku 4.5 | $0.00040 | $0.00261 |
Grade A, and why
colombia-conflict-broomva 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 26d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
colombia-conflict — CEV final-report knowledge engine
A permanent, queryable knowledge layer distilled from the Colombian Truth Commission's final report Hay Futuro Si Hay Verdad (2022 — 11 tomos / 24 books / ~8,900 pp / ~3.67M words). It carries the report's substantive learnings and insights, and gives agents tools to act on the problematics the report describes — above all, the goal of no repetición (non-repetition).
Architecture (kg / LLM-wiki)
Mirrors the workspace's kg LLM-as-index pattern:
- Substrate (canonical) —
references/: the 12 per-volume digests +synthesis.md(master consolidation) +lexicon.md. These are the knowledge pages; the agent reasons over them. - Full-text grounding —
references/fulltext/*.txt.gz: the complete extracted text of all 24 volumes (~3.67M words, gzipped ~7.7 MB).cc.py sourcegreps this for verbatim source passages — the digests summarize, the full text lets you quote the report exactly. - Source binaries (on demand) —
sources/MANIFEST.jsonlists the 11 downloadable units (10 digital PDFs + the Colombia-adentro ZIP, each with sha256).scripts/fetch_sources.shpulls + verifies the 385 MB of PDFs when actually needed; they are deliberately not committed. - Projection (routing) —
references/knowledge-index.md: a dense, one-line- per-item catalog auto-generated fromdata/+ digest headers. Tier-1 retrieval scores against this. - Structured data —
data/:statistics.json(the conflict universe),actors.json(collective-responsibility shares),recommendations.json(67 recs / 8 blocks),concepts.json(the coined lexicon). - Engine —
scripts/cc.py: two-tierload(catalog tier-1 → body-grep tier-2), data queries, thealignnon-repetition scorer, and the catalog generator. The agent is the query engine —loadsurfaces the relevant pages; the agent does the reasoning.
When to reach for it
Load this skill whenever a task touches the Colombian armed conflict or its aftermath — peacebuilding, transitional justice, victims and reparation, paramilitarism, the FARC-EP/ELN, drug policy, the land/agrarian question, the enemigo interno, falsos positivos, the UP genocide, social-leader killings, differential harms (ethnic peoples, women/LGBTIQ+, children, exiles, campesinado), territorial/human security, memory, or non-repetition — and whenever you must ground a claim in a sourced statistic, responsibility share, recommendation, or coined concept rather than guessing.
What ships with it
29 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.
- .gitignore 34 B
- CHANGELOG.md 1.6 KB
- data/actors.json 5.6 KB
- data/concepts.json 11 KB
- data/recommendations.json 10 KB
- data/statistics.json 8.8 KB
- LICENSE 1.1 KB
- README.md 2.6 KB
- references/digests/01-02-apex.md 24 KB
- references/digests/03-historia.md 17 KB
- references/digests/04-violaciones.md 21 KB
- references/digests/05a-territorial-crosscut.md 19 KB
- references/digests/05b-territorial-andean.md 21 KB
- references/digests/05c-territorial-south.md 16 KB
- references/digests/06-impactos.md 18 KB
- references/digests/07-testimonial.md 15 KB
- references/digests/08-etnico.md 16 KB
- references/digests/09-genero.md 18 KB
- references/digests/10-ninez.md 18 KB
- references/digests/11-exilio.md 21 KB
- references/knowledge-index.md 11 KB
- references/lexicon.md 6.0 KB
- references/synthesis.md 19 KB
- scripts/build_manifest.py 5.9 KB runs code
- scripts/cc.py 17 KB runs code
- scripts/fetch_sources.sh 2.0 KB runs code
- sources/MANIFEST.json 4.4 KB
- tests/requirements-dev.txt 12 B
- tests/test_cc.py 8.3 KB runs code
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.
- 26d ago First seen · 180 lines · 404 tokens per session scan A 5234fa1c4d8a
colombia-conflict-broomva is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 404 tokens to every session and 2,610 once invoked, about $0.0016 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 2026-10-02.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…