Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add synaptiai/synapti-marketplace/plugin install dossierWrote 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/synaptiai/synapti-marketplace/status)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/status"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/status/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/synaptiai/synapti-marketplace/status"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/status.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 | $0.00043 | $0.02456 |
| Opus 5 | $0.00022 | $0.01228 |
| Sonnet 5 | $0.00009 | $0.00491 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Status
Read-only observation. No skills, no agents, no writes.
Required Skills
None — read-only status command. No skill invocations.
References
Gather State
_RAW="$ARGUMENTS"
ARG1="${_RAW%% *}"
case "$ARG1" in
--json) MODE=json ;;
*) MODE=compact ;;
esac
__dr="${CLAUDE_PLUGIN_ROOT:-}"
[ -x "$__dr/bin/dossier-resolve-config.sh" ] || __dr=$({ echo plugins/dossier; ls -d "$HOME"/.claude/plugins/cache/synapti-marketplace/dossier/*/ 2>/dev/null | sort -Vr; echo "$HOME/.claude/plugins/marketplaces/synapti-marketplace/plugins/dossier"; } | while read -r __p; do [ -x "${__p%/}/bin/dossier-resolve-config.sh" ] && { echo "${__p%/}"; break; }; done)
echo "### Mode"
echo "STATUS_MODE=$MODE"
echo "### Plugin"
if [ ! -x "$__dr/bin/dossier-resolve-config.sh" ] || [ ! -x "$__dr/bin/dossier-staleness-check.sh" ]; then
echo "STATUS_STATE=blocked"
echo "STATUS_ERROR=dossier plugin scripts not found — reinstall or upgrade the plugin"
true; exit 0
fi
R="$__dr/bin/dossier-resolve-config.sh"
echo "PLUGIN_VERSION=$(jq -r '.version // "unknown"' "$__dr/.claude-plugin/plugin.json" 2>/dev/null)"
echo "### Package"
OUTPUT_ROOT=$("$R" --default "docs/dossier" dossier.project.outputRoot 2>/dev/null)
echo "OUTPUT_ROOT=$OUTPUT_ROOT"
if [ ! -d "$OUTPUT_ROOT/00-control" ]; then
echo "PACKAGE_STATE=absent"
echo "PACKAGE_HINT=run /dossier:init to scaffold, then /dossier:baseline to draft"
true; exit 0
fi
echo "PACKAGE_STATE=present"
echo "PROJECT_NAME=$("$R" --default '(unset)' dossier.project.name 2>/dev/null)"
echo "DELIVERY_MODE=$("$R" --default full dossier.engagement.deliveryMode 2>/dev/null)"
echo "DISCLOSURE_POLICY=$("$R" --default internal-only dossier.disclosure.policy 2>/dev/null)"
echo "### Coverage"
EXPECTED=23
FOUND=$(find "$OUTPUT_ROOT" -mindepth 2 -name '*.md' -type f 2>/dev/null | wc -l | tr -d ' ')
echo "CANONICAL_EXPECTED=$EXPECTED"
echo "CANONICAL_FOUND=$FOUND"
for d in 00-control 01-project 02-architecture 03-assurance 04-operating 05-due-diligence 06-public 07-verification; do
echo "DIR_${d}=$(find "$OUTPUT_ROOT/$d" -name '*.md' -type f 2>/dev/null | wc -l | tr -d ' ')"
done
echo "### Document status"
for s in verified "partially verified" draft "N/A"; do
n=$(grep -rl "^status: $s" "$OUTPUT_ROOT" --include='*.md' 2>/dev/null | wc -l | tr -d ' ')
echo "STATUS_$(printf '%s' "$s" | tr ' ' '_')=$n"
done
echo "### Registers"
C="$OUTPUT_ROOT/00-control"
echo "EVIDENCE_ROWS=$(grep -c '^| EV-' "$C/evidence-ledger.md" 2>/dev/null || echo 0)"
for st in V C R I U; do
echo "EVIDENCE_STATE_${st}=$(awk -F'|' '/^\| EV-/{gsub(/ /,"",$4); if($4=="'"$st"'") n++} END{print n+0}' "$C/evidence-ledger.md" 2>/dev/null || echo 0)"
done
echo "OPEN_QUESTIONS=$(grep -c '^| AQ-' "$C/assumptions-questions-and-contradictions.md" 2>/dev/null || echo 0)"
echo "CONTRADICTIONS=$(grep -c '^| CT-' "$C/assumptions-questions-and-contradictions.md" 2>/dev/null || echo 0)"
echo "NEEDS_OWNER=$(grep -c 'needs-owner' "$C/assumptions-questions-and-contradictions.md" 2>/dev/null || echo 0)"
echo "CLAIMS_TOTAL=$(grep -c '^| CL-' "$C/claim-and-disclosure-register.md" 2>/dev/null || echo 0)"
echo "CLAIMS_PENDING=$(grep -c '^| CL-.*| *pending *|' "$C/claim-and-disclosure-register.md" 2>/dev/null || echo 0)"
echo "TERMS=$(grep -c '^| TM-' "$C/terminology-and-ownership.md" 2>/dev/null || echo 0)"
echo "UNASSIGNED_OWNERS=$(grep -c 'unassigned' "$C/terminology-and-ownership.md" 2>/dev/null || echo 0)"
echo "### Staleness"
if [ -x "$__dr/bin/dossier-staleness-check.sh" ]; then
"$__dr/bin/dossier-staleness-check.sh" --output-root "$OUTPUT_ROOT" \
| grep -E '^(STALENESS_THRESHOLD_DAYS|DOCUMENTS_STALE|DOCUMENTS_UNDATED|OLDEST_VERIFICATION)='
else
echo "STALENESS_THRESHOLD_DAYS=unknown"
echo "DOCUMENTS_STALE=unknown"
echo "DOCUMENTS_UNDATED=unknown"
echo "OLDEST_VERIFICATION=unknown"
fi
echo "### Verification"
VR="$OUTPUT_ROOT/07-verification/documentation-verification-report.md"
if [ -f "$VR" ]; then
echo "AUDIT_ROUNDS=$(grep -c '<!-- DOSSIER_AUDIT' "$VR" 2>/dev/null || echo 0)"
echo "FINDINGS_OPEN=$(grep -cE '\bOpen\b' "$VR" 2>/dev/null || echo 0)"
echo "LAST_GATE_VERDICT=$(grep -m1 'GATE_VERDICT=' "$VR" 2>/dev/null | cut -d= -f2 || echo none)"
else
echo "AUDIT_ROUNDS=0"
echo "LAST_GATE_VERDICT=never-run"
fi
echo "### Refresh cursor"
ST="$OUTPUT_ROOT/.dossier-state.json"
if [ -f "$ST" ]; then
CURSOR=$(jq -r '.last_documented_sha // empty' "$ST" 2>/dev/null)
echo "CURSOR=${CURSOR:-none}"
if [ -n "$CURSOR" ] && git cat-file -e "${CURSOR}^{commit}" 2>/dev/null; then
echo "COMMITS_BEHIND=$(git rev-list --count "${CURSOR}..HEAD" 2>/dev/null || echo unknown)"
else
echo "COMMITS_BEHIND=unknown"
fi
else
echo "CURSOR=none"
fi
echo "### Automation"
WF=.github/workflows/dossier-docs-refresh.yml
echo "CI_ENABLED=$("$R" --default true dossier.ci.enabled 2>/dev/null)"
echo "WORKFLOW_PRESENT=$([ -f "$WF" ] && echo true || echo false)"
if [ -f "$WF" ] && [ -x "$__dr/bin/dossier-managed-file.sh" ]; then
"$__dr/bin/dossier-managed-file.sh" --verify "$WF" 2>/dev/null || echo "MANAGED=unknown"
echo "WORKFLOW_EXPECTED_VERSION=$("$R" --default unknown dossier.ci.expectedPluginVersion 2>/dev/null)"
fi
echo "TRIGGER_POLICY=$("$R" --default path-filtered dossier.ci.triggerPolicy 2>/dev/null)"
echo "ROLLING_BRANCH=$("$R" --default docs/dossier dossier.ci.rollingBranch 2>/dev/null)"
true
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.
- 6d ago First seen · 173 lines · 0 tokens per session scan A 9863fc07393c
status is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,456 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
paper-trail-ingest-all
Batch INGEST across the entire vault. Scans all SOTAs, identifies those with bibliographic sections containing free-text citations, then runs /paper-trail:ingest on each one sequentially. Reports per-SOTA summary at the end. The single batch entry point to make a legacy vault fully conform to the paper-trail pipeline.
paper-trail-inject-url
Injecte une URL OA connue (HAL, dépôt uni, NIME, page perso) pour une ref dont la cascade automatique a échoué, puis relance l'acquisition + validation page 1.
paper-trail-acquire
Troisième passe du pipeline cible refondu. Lance la cascade PDF (10 sources : Crossref OA + arXiv + OpenAlex + Unpaywall + HAL + CORE + éditeur par DOI + archive.org + WebSearch ; jusqu'à 17 avec les voies par navigateur et les sources étendues opt-in) ciblée sur les refs d'un SOTA donné. Différent de pipeline run qui…
paper-trail-cascade
Acquire PDFs via the 8-source cascade (11 with opt-in extended sources) for a single ref by slug, or a batch filtered by state. Validates page 1 anti-homonymy on each download.
create-worktree
Follow these steps to create a git worktree.
show
Display a past OCR review session.