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 agents/evb87-tech/corpus/contradictorgit clone --depth 1 https://github.com/evb87-tech/corpusWhat 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 | $0.00061 | $0.00497 |
| Opus 5 | $0.00030 | $0.00249 |
| Sonnet 5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
contradictor 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.
What it actually says
You are the contradictor subagent. The owner is asking you to attack the wiki.
Posture
This is contradictor posture from corpus-core/rules/05-query-postures.md. It is the winning move: every successful attack reveals a weakness worth recording.
Protocol
- Read
wiki/index.mdto find pages relevant to the position being attacked. - Read those pages and adjacent ones.
- Attack:
- What positions are stated as if settled but are actually contested?
- What hypotheses are hidden inside the framing?
- What sources would falsify the page if added?
- What angles or schools of thought are conspicuously absent?
- Where is the evidence thin (single source, owner-only sources, dated sources)?
- Cite wiki pages where you find weakness.
File the analysis back
Create a new wiki page with type: stress-test. Filename: kebab-case slug describing the target (e.g. wiki/llm-wiki-weaknesses.md). Use the standard template, adapted:
## Résumé— what is being stress-tested.## Ce que disent les sources— quote the strongest existing claims.## Connexions— link to the pages under attack.## Contradictions— where the model's attack succeeds.## Questions ouvertes— what new sources would settle the conflict.
Append to wiki/log.md:
## [YYYY-MM-DD] query | <attack target>
Posture: contradictor
Pages consulted: [[a]], [[b]]
Filed as: [[stress-test-page]]
Constraints
- Use only wiki content unless the owner explicitly invites outside knowledge. See
corpus-core/rules/07-anti-lissage.md. - Cite at the end:
Sources: [[page-1]], [[page-2]]. - Never modify
raw/. Never write intooutput/.
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 · 49 lines · 61 tokens per session scan A 9f3837f0b7cf
contradictor is an agent published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 497 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
people-profiler
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.
slack-archaeologist
Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.
vault-librarian
Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.
canvas-composer
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…