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 skills/evb87-tech/corpus/roadmap-updatenpx skills add evb87-tech/corpus --skill roadmap-updategit 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 | $0.00094 | $0.01966 |
| Opus 5 | $0.00047 | $0.00983 |
| Sonnet 5 | $0.00019 | $0.00393 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
roadmap-update 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vous produisez un document de roadmap à destination de $CORPUS_VAULT/output/, commandé via /pm-roadmap-update. L'argument optionnel $ARGUMENTS fournit un titre ou un périmètre (ex. : « Q2 orienté clients »).
Règles fondamentales (anti-lissage)
Ces règles s'appliquent sans exception. Voir corpus-core/rules/07-anti-lissage.md.
- Ne jamais inventer une priorité. Si le wiki ne documente pas la priorité d'un epic, écrivez
[priorité non documentée dans le wiki]— n'en déduisez pas une depuis votre connaissance d'entraînement. - Ne jamais compléter silencieusement. Si le wiki est vide de décisions, dites-le explicitement. Ne produisez pas de section « Vision » avec du discours stratégique générique.
- Ne jamais harmoniser les contradictions. Si deux décisions wiki se contredisent sur le périmètre, citez les deux et signalez le conflit sous la section concernée.
- Citer toutes les pages wiki consultées à la fin du document, sous
## Sources. - La roadmap est un livrable
output/. Elle ne doit jamais être déposée danswiki/. Voircorpus-core/rules/01-folder-discipline.md.
Étape 1 — Vérifier la présence de bd
Avant toute chose, vérifiez que la commande bd est disponible dans le runtime :
which bd 2>/dev/null || echo "ABSENT"
Si bd est absent, refusez avec le message suivant et arrêtez :
Erreur :
bdest introuvable dans le runtime. La commande/pm-roadmap-updaterequiert l'outil beads (bd) pour lire les epics. Installez-le : https://github.com/draftcode/beads (ou suivez les instructions de votre équipe). Une fois installé, relancez/pm-roadmap-update.
Étape 2 — Lire les epics beads
Exécutez :
bd list --type epic --json --limit 0
Le flag --json est un flag global de bd ; --limit 0 désactive la pagination (50 par défaut).
Si la commande échoue (erreur de base de données, répertoire .beads absent, etc.), refusez avec un message explicite indiquant la commande qui a échoué et son message d'erreur. Ne continuez pas.
What ships with it
1 file 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.
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 · 199 lines · 94 tokens per session scan A ed3915d15a58
roadmap-update is a skill published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 94 tokens to every session and 1,966 once invoked, about $0.0005 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 skills, from other repositories
project-flow-ops
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
ariadne:workstream-tracking
Create, audit, or improve Obsidian Kanban work boards and Dataview dashboards for durable project, roadmap, evaluation, implementation, QA, or recurring workstream tracking inside an agent-maintained vault.
issue-match
Measure a TARGET repository's queue + find a LIVE door (an open issue matching our artifact) BEFORE pushing a PR there. Trigger on "/issue-match", "is this repo worth a PR", "measure the queue", "find a live issue". Answers "knock here or skip": how many open PRs, how many of the last N closed ones were actually…
project-sync
On-demand AI-powered sync of a project's repo state into the brain vault. Reads live git/GitHub/Jira data, updates the project status doc, and makes targeted edits to relevant brain docs where content is clearly stale. Triggered by "/project-sync [name]", "sync [project]", "what's the current state of [project]".
triage-tasks
Use when you want to review and batch-update open vault task statuses for the current project or across all projects.
tackle-task
Use when starting work on a specific vault task, when a task title or path is mentioned, or when coming from triage output.