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.
git clone --depth 1 https://github.com/evb87-tech/corpusWrote 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/commands/evb87-tech/corpus/ingest-02-edge-contradiction)<a href="https://agentmods.dev/commands/evb87-tech/corpus/ingest-02-edge-contradiction"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/ingest-02-edge-contradiction/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/commands/evb87-tech/corpus/ingest-02-edge-contradiction"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/ingest-02-edge-contradiction.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 | $0.00000 | $0.00703 |
| Opus 5 | $0.00000 | $0.00351 |
| Sonnet 5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
ingest-02-edge-contradiction 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scénario
Deux sources déjà ingérées traitent du même concept (la valeur du feedback utilisateur
en sprint review) mais arrivent à des conclusions opposées. Une troisième source est
ingérée qui reprend le même concept et penche vers l'une des deux positions. Le
comportement attendu est que la page wiki existante conserve la section ## Contradictions
avec les deux attributions distinctes, que la nouvelle source soit ajoutée à sources:
et citée, et qu'aucune harmonisation silencieuse ne soit opérée.
Setup
Créer les fichiers suivants dans $CORPUS_VAULT/raw/ et ingérer les deux premiers avant
de lancer le prompt de l'éval :
raw/cmd-edge-source-a.md (voir evals/fixtures-commands/cmd-edge-source-a.md) :
Affirme que le feedback recueilli en sprint review doit être intégré directement dans
le backlog de la prochaine itération.
raw/cmd-edge-source-b.md (voir evals/fixtures-commands/cmd-edge-source-b.md) :
Affirme que le feedback de sprint review doit d'abord passer par une phase de
qualification avant d'entrer dans le backlog, pour éviter la pollution du backlog.
Ingérer les deux sources :
/ingest raw/cmd-edge-source-a.md
/ingest raw/cmd-edge-source-b.md
Vérifier que la page wiki résultante (ex. wiki/sprint-review.md) contient bien une
section ## Contradictions. Puis créer :
raw/cmd-edge-source-c.md (voir evals/fixtures-commands/cmd-edge-source-c.md) :
Affirme que le feedback de sprint review doit être intégré directement (position A),
mais ajoute une précision : seul le feedback des utilisateurs actifs est éligible.
Prompt
/ingest raw/cmd-edge-source-c.md
Pass criteria (rubric)
- La page wiki existante est modifiée (non dupliquée).
sources:inclut désormais les trois fichiers raw. - La section
## Contradictionsreste présente et cite toujours les deux positions opposées (source-a contre source-b). La nouvelle source (source-c) est mentionnée comme renforçant la position de source-a avec une nuance. - Aucune phrase du type « les approches divergent mais en pratique » ou « les deux méthodes peuvent être réconciliées » n'apparaît sans attribution explicite à une source.
- Le récapitulatif final mentionne au moins 1 contradiction détectée.
wiki/log.mdest mis à jour.
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.
- 9d ago First seen · 71 lines · 0 tokens per session scan A d5076a85d566
ingest-02-edge-contradiction is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 703 tokens. 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 commands, from other repositories
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.
open
Open the memex vault in Finder or Obsidian.
sol
Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.
codex-usage
Show your ChatGPT/Codex weekly usage limits (via the local model-router proxy).
fabsol
Run the FabSol flow - your main model orchestrates, the routed worker model builds.