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/socialgouv/egapro/docnpx skills add SocialGouv/egapro --skill docgit clone --depth 1 https://github.com/SocialGouv/egaproWrote 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/socialgouv/egapro/doc)<a href="https://agentmods.dev/skills/socialgouv/egapro/doc"><img src="https://agentmods.dev/badge/skills/socialgouv/egapro/doc.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01698 |
| Opus 5 | $0.00026 | $0.00849 |
| Sonnet 5 | $0.00011 | $0.00340 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
doc 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 yesterday.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/doc
Régénération de la documentation utilisateur du repo. Le skill délègue à l'agent doc-writer qui réécrit docs/features.md, docs/architecture.md, et docs/parcours-utilisateurs.md à partir de l'état courant du code.
Le skill est l'entrée humaine ; l'entrée orchestrée (en fin d'epic) passe par scripts/orchestration/run_doc_writer.sh invoqué directement depuis epic_loop.sh.
| Mode d'invocation | Comportement |
|---|---|
/doc sans argument |
Tourne sur la branche courante. Compare HEAD vs origin/alpha. Commit local seulement — l'humain pousse lui-même. |
/doc <issue#> |
Tourne sur la branche d'un ticket / epic. Si <issue#> est un epic, opère sur origin/epic/<N>. Sinon opère sur la branche linkée à l'issue (sidebar Development). Commit + push automatique. |
Step 0 — Pré-conditions
Refuser si :
- Le working tree est dirty (
git status --porcelainnon-vide) → demander à l'humain de commit/stash d'abord - La branche courante est
alphaoumasterdirectement → la doc est régénérée sur les branches feature, pas sur la branche stable
if [ -n "$(git status --porcelain)" ]; then
echo "Working tree dirty — commit ou stash d'abord."
exit 1
fi
CURRENT=$(git branch --show-current)
if [ "$CURRENT" = "alpha" ] || [ "$CURRENT" = "master" ]; then
echo "Refus : /doc ne tourne pas directement sur $CURRENT. Crée une branche dédiée."
exit 1
fi
Step 1 — Résoudre la branche cible
Sans argument
Branche cible = branche courante. Base de comparaison = origin/alpha.
git fetch origin alpha --quiet
TARGET_BRANCH=$(git branch --show-current)
BASE_BRANCH=alpha
EPIC_N=null
PUSH_AUTO=false # commit local, l'humain push lui-même
Avec un argument <issue#>
ISSUE_N="${ARGUMENTS%% *}"; ISSUE_N="${ISSUE_N#\#}"
ISSUE_TYPE=$(gh issue view "$ISSUE_N" --json issueType --jq '.issueType.name')
if [ "$ISSUE_TYPE" = "Feature" ]; then
# Epic → tourne sur la branche d'intégration
TARGET_BRANCH="epic/$ISSUE_N"
BASE_BRANCH=alpha
EPIC_N="$ISSUE_N"
else
# Task / Bug → trouver la branche linkée à l'issue
TARGET_BRANCH=$(gh api graphql -f query='
query($owner:String!, $repo:String!, $n:Int!) {
repository(owner:$owner, name:$repo) {
issue(number:$n) {
linkedBranches(first:5) { nodes { ref { name } } }
}
}
}' -f owner=SocialGouv -f repo=egapro -F n=$ISSUE_N \
--jq '.data.repository.issue.linkedBranches.nodes[0].ref.name // empty')
if [ -z "$TARGET_BRANCH" ]; then
echo "Aucune branche linkée à l'issue #$ISSUE_N."
exit 1
fi
# Base = parent epic si l'issue est sub-issue d'un epic, sinon alpha
PARENT=$(gh api graphql -f query='...parent...' --jq '.parent.number // empty')
if [ -n "$PARENT" ]; then
BASE_BRANCH="epic/$PARENT"
else
BASE_BRANCH=alpha
fi
EPIC_N="${PARENT:-null}"
fi
PUSH_AUTO=true
git fetch origin "$TARGET_BRANCH" "$BASE_BRANCH" --quiet
git checkout "$TARGET_BRANCH"
git pull --ff-only origin "$TARGET_BRANCH"
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.
- yesterday First seen · 165 lines · 53 tokens per session scan A 13e557370a1b
doc is a skill published in the GitHub repository SocialGouv/egapro (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,698 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 2026-09-04.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
commit
Commit current changes with a clear, descriptive message.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…