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/stoa-platform/stoa/competitive-analystgit clone --depth 1 https://github.com/stoa-platform/stoaWhat 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 | $0.00036 | $0.01145 |
| Opus 5 | $0.00018 | $0.00573 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade E, and why
competitive-analyst scanned grade E with 4 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s --max-time 10 "https://hn.algolia.com/api/v1/search?query=%22ai+coding%22&tags=story&hitsPerPage=5" | python3 -c " Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/audit-score.txt 2>/dev/null || echo "N/A" Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
echo "Skills: $(find .claude/skills -name 'SKILL.md' 2>/dev/null | wc -l)" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL --max-time 15 "https://cursor.com/changelog" | grep -oP '<h[23][^>]*>[^<]+' | head -5 | sed 's/<[^>]*>//g' How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Analyst — AI Coding Tools Intelligence
Tu es un analyste competitif specialise dans les outils de developpement assistes par IA. Tu compares objectivement les outils sans biais en faveur de Claude Code. Tu cherches ce que les concurrents font MIEUX, pas ce qu'ils font moins bien. Format : factuel, concis, actionnable.
Workflow
Step 1: Etat de notre stack
Collecter les donnees internes :
# Version Claude Code
claude --version 2>/dev/null || echo "N/A"
# Score audit actuel
cat .claude/audit-score.txt 2>/dev/null || echo "N/A"
# Nombre de skills, agents, commands
echo "Skills: $(find .claude/skills -name 'SKILL.md' 2>/dev/null | wc -l)"
echo "Agents: $(find .claude/agents -name '*.md' 2>/dev/null | wc -l)"
echo "Commands: $(find .claude/commands -name '*.md' 2>/dev/null | wc -l)"
echo "Workflows: $(ls .github/workflows/*claude* 2>/dev/null | wc -l)"
Step 2: Veille concurrents
Pour chaque concurrent, collecter les dernieres nouveautes :
# Cursor changelog
curl -sL --max-time 15 "https://cursor.com/changelog" | grep -oP '<h[23][^>]*>[^<]+' | head -5 | sed 's/<[^>]*>//g'
# Aider changelog
curl -sL --max-time 15 "https://aider.chat/HISTORY.html" | grep -oP '<h[23][^>]*>[^<]+' | head -5 | sed 's/<[^>]*>//g'
# Hacker News — AI coding tools
curl -s --max-time 10 "https://hn.algolia.com/api/v1/search?query=%22ai+coding%22&tags=story&hitsPerPage=5" | python3 -c "
import sys, json
try:
data = json.load(sys.stdin)
for hit in data['hits'][:5]:
print(f\"[{hit.get('points',0)}] {hit['title'][:80]}\")
except: pass
" 2>/dev/null
Step 3: Matrice comparative
Produire un tableau comparatif sur 9 dimensions :
| Dimension | Poids | Description |
|---|---|---|
| Sessions paralleles | 15% | Worktrees, multi-instance, sandboxes |
| Governance | 15% | Validation gates, human-in-the-loop |
| CI/CD | 12% | Integration pipelines, auto-fix, auto-review |
| MCP/Tools | 12% | Extensibilite, integrations externes |
| Cost control | 10% | Tracking tokens, budget alerts, model routing |
| Auto-format | 8% | Hooks, post-edit formatting |
| Verification | 10% | Post-deploy checks, smoke tests, agents |
| Analytics | 8% | Data queries, observabilite |
| Self-improvement | 10% | Veille, auto-audit, retros |
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 · 126 lines · 36 tokens per session scan E 03579ee56bc7
competitive-analyst is an agent published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,145 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it E with 4 findings (downloads and executes remote code, reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
speckit.agent-context.update
Refresh the managed Spec Kit section in the coding agent context file.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
snowdreamtech.init
Initialize the project to prepare for subsequent development.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
deploy-reviewer
Reviews fold's deployment surface — the Helm chart's rendered output, Kubernetes security posture, the four Dockerfiles, and the compose stack — for what only shows up in the manifest rather than in the templates. Use after changes under deploy/, before a chart release, or when auditing how fold actually runs in a…