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/agent-engineer-master/skill-engineer/analyze-trajectorynpx skills add Agent-Engineer-Master/skill-engineer --skill analyze-trajectorygit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/analyze-trajectory)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/analyze-trajectory"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/analyze-trajectory.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 | $0.00210 | $0.02518 |
| Opus 5 | $0.00105 | $0.01259 |
| Sonnet 5 | $0.00042 | $0.00504 |
| Haiku 4.5 | $0.00021 | $0.00252 |
Grade C, and why
analyze-trajectory scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer --> How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Trajectory
For a defined industry, analyze direction of travel: dual S-curve position, Three Horizons portfolio overlay on G3 sub-segments, discontinuities, Helmer Power Progression, and base/bear/bull scenarios. Output: trajectory.md.
The discipline: trajectory is not extrapolation. Linear continuation past an inflection is the most common failure mode. Every assessment must name the diagnostic signal, the timing window, and the swing variable that could falsify it.
Iron rules:
- Every claim about trajectory carries a V/C/A/I tag — see
../_shared/provenance-tagging.md. - Dual S-curve mandatory — assess BOTH market-adoption lifecycle AND technology lifecycle. They desynchronize. Skipping either = analysis failure.
- ≥3 G3 sub-segments classified into H1 / H2 / H3 (consume from size-market when present).
- ≥2 discontinuities named with explicit year-range timing windows (e.g., "2026-2028"). "Soon" / "coming" / "eventually" fail validation.
- Power Progression: name which of Helmer's 7 Powers are buildable NOW, in YEAR 3, in YEAR 5, and which are CLOSED. Late entrants cannot build Counter-Positioning in a mature industry.
- Scenarios: base / bear / bull with ≥3 named swing variables (not "growth higher / growth lower"). Swing variables must be independent and falsifiable.
- 5-year forward horizon is the default; longer horizons require explicit justification.
Process
1. Intake
Confirm: industry slug, geographic scope, 5-year horizon (or justified alternative), and G3 sub-segment source. Check working/market-sizing.md in the same industry folder. If present, extract the G3 sub-segment table for Step 3 consumption. If absent (standalone mode), ask the user to supply ≥3 named sub-segments OR run size-market first. Record the source in the output header ("G3 source: working/market-sizing.md" or "G3 source: user-supplied at intake").
2. Dual S-curve assessment
Read references/s-curve-methodology.md. Produce TWO assessments:
What ships with it
10 files 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.
- assets/trajectory-template.md 4.1 KB
- evals/evals.json 4.9 KB
- references/discontinuities-catalog.md 3.6 KB
- references/edge-cases.md 3.0 KB
- references/learnings.md 2.3 KB
- references/power-progression.md 3.7 KB
- references/s-curve-methodology.md 5.2 KB
- references/scenario-methodology.md 4.6 KB
- references/three-horizons.md 2.8 KB
- scripts/validate_trajectory.py 13 KB runs code
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.
- 3d ago First seen · 122 lines · 210 tokens per session scan C 46752e7c353c
analyze-trajectory is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 210 tokens to every session and 2,518 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.